Skip to content
← Registry
Trust Report

8004-agent

22
REJECTED
Format: openclawScanner: v0.8.0Duration: 71msScanned: 5d ago · Jun 2, 11:56 AMSource →
Embed this badge
AgentVerus REJECTED 22AgentVerus REJECTED 22AgentVerus REJECTED 22
[![AgentVerus](https://agentverus.ai/api/v1/skill/5cdfd875-7c18-4559-b2a8-31b320a9d261/badge)](https://agentverus.ai/skill/5cdfd875-7c18-4559-b2a8-31b320a9d261)
Community Discussion

Community Comments

Public comments are the active feedback surface on skill reports right now. Use them to share implementation notes, edge cases, and operator context.

0 comments

Sign in to comment on this skill

No comments yet. Be the first to share your thoughts.

Continue the workflow

Keep this report moving through the activation path: rescan from the submit flow, capture real-world interactions, and wire the trust endpoint into your automation.

https://agentverus.ai/api/v1/skill/5cdfd875-7c18-4559-b2a8-31b320a9d261/trust
Personalized next commands

Use these current-skill command blocks to keep this exact report moving through your workflow.

Record an interaction
curl -X POST https://agentverus.ai/api/v1/interactions \
  -H "Authorization: Bearer at_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"agentPlatform":"openclaw","skillId":"5cdfd875-7c18-4559-b2a8-31b320a9d261","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/5cdfd875-7c18-4559-b2a8-31b320a9d261/trust

Category Scores

19
Permissions
100
Injection
7
Dependencies
45
Behavioral
85
Content
80
Code Safety

Findings (28)

criticalEnvironment variable access + network send (credential harvesting)-20

Code accesses process.env and makes outbound network requests. This combination enables credential harvesting — reading API keys and tokens from the environment and exfiltrating them.

const PROXY_URL = process.env.KEYRING_PROXY_URL;

Review the code for legitimate use. If this is instructional, consider adding a safety disclaimer.

code-safetyASST-05
highCapability contract mismatch: inferred credential access is not declared-15

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: reads `KEYRING_PROXY_URL` and `KEYRING_PROXY_SECRET

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-05
highCapability contract mismatch: inferred command execution is not declared-12

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: exec

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highCapability contract mismatch: inferred container runtime control is not declared-10

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: docker build

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highRemote browser delegation detected-15

Found remote browser delegation pattern: "proxy support"

- **`@buildersgarden/siwa/keystore`** — Secure key storage abstraction with keyring proxy support

Treat cloud or remote browser execution as external data egress. Be explicit about what page content, cookies, or secrets may leave the local machine, and require user approval before delegating authenticated sessions.

behavioralASST-02
mediumCapability contract mismatch: inferred file write is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: Create a JSON file

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred file read is not declared-6

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: Reference Files

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred network access is not declared-6

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: http://keyring-proxy:3100

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-04
mediumCapability contract mismatch: inferred local service access is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: http://localhost:3100

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred documentation ingestion is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: reference implementation

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred package bootstrap is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: npx create-8004-agent

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumHosted browser service dependency-8

The skill depends on a hosted or proxy-backed browser service, which introduces an external execution surface and additional dependency trust requirements.

proxy support

Review which external services or providers the skill depends on, what data crosses that boundary, and whether the dependency is necessary for the intended workflow.

dependenciesASST-04
mediumExternal documentation dependency-8

The skill relies on external documentation, specs, or README content as part of its workflow, which introduces an additional remote dependency and trust boundary.

reference implementation

Review which external services or providers the skill depends on, what data crosses that boundary, and whether the dependency is necessary for the intended workflow.

dependenciesASST-04
mediumFinancial/payment actions detected-10

Found financial/payment actions pattern: "send funds"

1. **Show the user the wallet address and the target chain** so they can send funds:

Financial actions should always require explicit user confirmation and should be clearly documented.

behavioralASST-09
mediumFinancial/payment actions detected-10

Found financial/payment actions pattern: "wallet"

needs to: (1) create or manage an Ethereum wallet for onchain identity, (2) register on the

Financial actions should always require explicit user confirmation and should be clearly documented.

behavioralASST-09
mediumMany external URLs referenced (13)-8

The skill references 13 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.

URLs: http://keyring-proxy:3100`, https://your-keyring-proxy.up.railway.app, https://railway.com/button.svg, https://railway.com/deploy/siwa-keyring-proxy?referralCode=ZUrs1W, https://your-keyring-proxy.up.railway.app`...

Minimize external dependencies to reduce supply chain risk.

dependenciesASST-04
mediumUnknown external reference-8

The skill references an unknown external domain which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Unknown external reference

http://keyring-proxy:3100`

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
mediumLocal service URL reference-8

The skill references a localhost or private-network service URL which is classified as medium risk.

http://localhost:3100

Review localhost/private-network service references carefully. Local service URLs can expose internal apps, admin panels, or developer tooling to agent-driven workflows.

dependenciesASST-04
mediumLocal service access detected (inside code block)-5

Found local service access pattern: "http://localhost:3100"

KEYRING_PROXY_URL=http://localhost:3100 # or your Railway URL

Treat localhost and loopback services as privileged local attack surfaces. Require explicit approval, constrain reachable ports, and avoid combining local access with session reuse or tunneling.

behavioralASST-03
mediumPackage bootstrap execution detected-5

Found package bootstrap execution pattern: "npx create-8004-agent" Merged overlapping signals from the repeated finding family: - Package bootstrap execution detected

npx create-8004-agent

Surface package bootstrap commands for review. Ephemeral package execution and install-time dependency pulls increase supply-chain risk, especially when versions are not pinned or provenance is unclear.

behavioralASST-04
mediumContainer runtime control detected (inside code block)-5

Found container runtime control pattern: "docker build"

docker build -f packages/keyring-proxy/Dockerfile -t keyring-proxy .

Treat Docker or container-runtime control as privileged host access. Scope container operations tightly, avoid arbitrary daemon access, and require explicit approval before mutating local workloads.

behavioralASST-03
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://railway.com/button.svg

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference

The skill references an unknown external domain which is classified as low risk.

https://railway.com/deploy/siwa-keyring-proxy?referralCode=ZUrs1W

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference

The skill references an unknown external domain which is classified as low risk.

https://your-keyring-proxy.up.railway.app`

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference

The skill references an unknown external domain which is classified as low risk.

https://siwa.builders.garden/docs/deploy

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference

The skill references an unknown external domain which is classified as low risk.

https://www.alchemy.com/faucets/ethereum-sepolia

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowMissing or insufficient description-5

The skill lacks a meaningful description, making it difficult to assess its purpose.

No description found

Add a clear, detailed description of what the skill does and what it needs access to.

contentASST-09
infoSafety boundaries defined

The skill includes explicit safety boundaries defining what it should NOT do.

Safety boundary patterns detected in content

Keep these safety boundaries. They improve trust.

contentASST-09