optimize-agents-md

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core design of reading and auditing existing instruction files.
  • Ingestion points: In SKILL.md (Stage 1), the agent is instructed to read AGENTS.md, CLAUDE.md, .claude/, .cursor/rules/, .cursorrules, and other project files.
  • Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings when reading these files.
  • Capability inventory: The skill has the capability to write and modify files (AGENTS.md, CLAUDE.md) as part of its Drafting (Stage 5) and Wiring (Stage 6) phases.
  • Sanitization: There is no mention of sanitizing, escaping, or validating the content extracted from these files before using it to generate new instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 04:26 PM
Security Audit — agent-trust-hub — optimize-agents-md