agents-md-triage

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes instructions from external documentation files (e.g., AGENTS.md, CLAUDE.md) which presents a potential indirect injection surface.
  • Ingestion points: The skill reads contents from AGENTS.md, CLAUDE.md, GEMINI.md, package.json, and other project files specified during triage (SKILL.md).
  • Boundary markers: Absent. The skill does not provide explicit delimiters or instructions to the agent to disregard commands embedded within the data it is auditing.
  • Capability inventory: The skill has capabilities for file reading, file deletion/modification, execution of shell commands (e.g., wc -l, just check), and git operations (SKILL.md).
  • Sanitization: Absent. There is no mention of sanitizing or escaping the text read from external files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:01 PM
Security Audit — agent-trust-hub — agents-md-triage