instructions-master

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists purely of markdown instructions and does not include any scripts, executables, or code files.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for reading and editing other skill files and evaluation data, which is a potential ingestion surface for untrusted content.
  • Ingestion points: Reads target instructions and evals/evals.json.
  • Boundary markers: Not explicitly defined.
  • Capability inventory: Implicitly uses the agent's file system and skill discovery tools.
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:38 AM
Security Audit — agent-trust-hub — instructions-master