check-coherence

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze external files for coherence. This creates a surface for indirect prompt injection where malicious instructions inside the processed file could attempt to influence the agent's behavior.
  • Ingestion points: The skill reads external instruction files as specified in Step 1 of SKILL.md.
  • Boundary markers: No specific delimiters or boundary instructions are used to isolate the file content from the agent's primary instructions.
  • Capability inventory: The skill performs analysis and proposes edits but does not exhibit dangerous capabilities such as network exfiltration, arbitrary command execution, or persistence mechanisms.
  • Sanitization: There is no evidence of input validation, filtering, or sanitization of the file content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 09:06 AM
Security Audit — agent-trust-hub — check-coherence