agents-md-improver
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read, integrate, and consolidate instructions from external files which constitutes an attack surface.
- Ingestion points: The skill reads
AGENTS.md,CLAUDE.md,.claude/CLAUDE.md, andGEMINI.mdfrom the repository root. - Boundary markers: No delimiters or safety instructions are used to prevent the agent from adopting malicious instructions found in these files.
- Capability inventory: The skill possesses the ability to read files, write patches, delete files, and create symlinks within the repository.
- Sanitization: There is no evidence of text validation or filtering for malicious prompt injection patterns during the consolidation process.
- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata with no accompanying executable scripts or binaries.
Audit Metadata