agent-md-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it reads and processes external, user-supplied files such as
AGENTS.md,CLAUDE.md, and project metadata to provide advice and modify content. Ingestion points: Specifically readsAGENTS.md,CLAUDE.md,README.md,package.json, and.github/workflows/during its diagnostic and optimization phases. Boundary markers: Does not define explicit delimiters to separate user data from instructions. Capability inventory: The skill is explicitly designed to perform file modifications (Editor mode) based on its analysis. Sanitization: No validation or sanitization is performed on the ingested file content.
Audit Metadata