init

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill reads untrusted data from the repository codebase to generate the AGENTS.md file, which presents an attack surface for indirect prompt injection.\n
  • Ingestion points: Processes content from various files including README.md, .cursorrules, .github/copilot-instructions.md, and CLAUDE.md.\n
  • Boundary markers: Absent. The instructions do not include delimiters or warnings to ignore malicious commands embedded in the analyzed files.\n
  • Capability inventory: File system write access (creating or modifying AGENTS.md based on analyzed content).\n
  • Sanitization: Absent. External file content is parsed and incorporated into the output without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM