Skip to content
← Registry
Trust Report

AgentVerus Skill Writer

Create a new `SKILL.md` by applying AgentVerus best practices (least privilege, explicit safety boundaries, clear output constraints) so the resulting skill is easier to trust and more likely to pass automated scans.

96
CONDITIONAL
Format: claudeScanner: v0.7.1Duration: 32msScanned: 4d ago · Apr 4, 3:00 PMSource →
Embed this badge
AgentVerus CONDITIONAL 96AgentVerus CONDITIONAL 96AgentVerus CONDITIONAL 96
[![AgentVerus](https://agentverus.ai/api/v1/skill/9745f7a6-71ed-4689-8b05-bd5a6b7b092e/badge)](https://agentverus.ai/skill/9745f7a6-71ed-4689-8b05-bd5a6b7b092e)
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/9745f7a6-71ed-4689-8b05-bd5a6b7b092e/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":"9745f7a6-71ed-4689-8b05-bd5a6b7b092e","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/9745f7a6-71ed-4689-8b05-bd5a6b7b092e/trust

Category Scores

92
Permissions
100
Injection
100
Dependencies
85
Behavioral
100
Content
100
Code Safety

Findings (5)

highAutonomous action without confirmation detected-15

Found autonomous action without confirmation pattern: "without confirmation"

- Prevent destructive actions without confirmation

Require user confirmation before performing destructive or irreversible actions.

behavioralASST-09
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: writes (files

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

permissionsASST-03
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
infoOutput constraints defined

The skill includes output format constraints (length limits, format specifications).

Output constraint patterns detected

Keep these output constraints.

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