analyze-docs

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Atlassian and Notion tools to perform searches and fetch pages. The target environment is explicitly defined, and no unauthorized data transmission was detected.
  • [SAFE]: The instructions contain strict constraints requiring the agent to 'extract definitions and rules as direct quotes' and 'never interpret or paraphrase'. This design mitigates the risk of indirect prompt injection by ensuring the agent treats document content as data rather than instructions.
  • [SAFE]: Analysis of the skill body and metadata revealed no evidence of obfuscation, malicious command execution, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 07:19 PM
Security Audit — agent-trust-hub — analyze-docs