readme

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted project metadata.\n
  • Ingestion points: package.json, composer.json, and other main project files (SKILL.md).\n
  • Boundary markers: None found.\n
  • Capability inventory: The skill instructs the agent to analyze structure and output markdown; no explicit tool definitions are present in SKILL.md.\n
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — readme