Skip to content
← Registry
Trust Report

sendook-openclaw

Read and send emails from an existing Sendook inbox. Use when an AI agent needs to check for new emails, read messages, reply to conversations, or send new emails from a pre-configured inbox. Limited to message operations only — no inbox creation, domain management, or webhook configuration.

71
SUSPICIOUS
Format: openclawScanner: v0.8.0Duration: 9msScanned: 6d ago · Jun 1, 7:10 PMSource →
Embed this badge
AgentVerus SUSPICIOUS 71AgentVerus SUSPICIOUS 71AgentVerus SUSPICIOUS 71
[![AgentVerus](https://agentverus.ai/api/v1/skill/42052e57-db5a-4be5-9475-3b4405c71eac/badge)](https://agentverus.ai/skill/42052e57-db5a-4be5-9475-3b4405c71eac)
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/42052e57-db5a-4be5-9475-3b4405c71eac/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":"42052e57-db5a-4be5-9475-3b4405c71eac","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/42052e57-db5a-4be5-9475-3b4405c71eac/trust

Category Scores

74
Permissions
75
Injection
36
Dependencies
70
Behavioral
95
Content
100
Code Safety

Findings (10)

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: shell

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

permissionsASST-03
highCredential access detected-25

Found credential access pattern: "credential file"

> **Important**: Always confirm with the user before reading any local file to attach. Only attach files the user has explicitly requested. Never read files outside the current working directory or pr

Remove references to credentials and secrets. Skills should never access sensitive authentication data.

injectionASST-05
highPotential data exfiltration: skill reads credentials and sends them to external endpoints-25

The skill contains patterns that actively read credential files and send data to external endpoints, suggesting a possible data exfiltration flow.

Active credential reading and suspicious network exfiltration patterns both present

Separate credential access from network operations. If both are needed, declare them explicitly and justify.

behavioralASST-06
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: https://github.com/obaid/sendook-skills

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

permissionsASST-04
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: npm install

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

permissionsASST-03
mediumMany external URLs referenced (10)-8

The skill references 10 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.

URLs: https://github.com/obaid/sendook-skills, https://www.npmjs.com/package/@sendook/node, https://github.com/getrupt/sendook, https://api.sendook.com/v1/inboxes/$SENDOOK_INBOX_ID/messages, https://api.sendook.com/v1/inboxes/$SENDOOK_INBOX_ID/messages?query=invoice...

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

https://api.sendook.com/v1/inboxes/$SENDOOK_INBOX_ID/messages

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
mediumPackage bootstrap execution detected (inside code block)-5

Found package bootstrap execution pattern: "npm install"

npm install @sendook/node

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
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
infoError handling instructions present

The skill includes error handling instructions for graceful failure.

Error handling patterns detected

Keep these error handling instructions.

contentASST-09