ai-agents-dot-md
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from existing documentation files, making it vulnerable to indirect prompt injection.
- Ingestion points: The skill reads user-provided or repository-based
AGENTS.mdfiles for analysis as defined inSKILL.md. - Boundary markers: The instructions do not define boundary markers to isolate the analyzed content from the agent's internal reasoning.
- Capability inventory: The skill provides the ability to modify local files through the
Applyaction inSKILL.md. - Sanitization: There is no explicit logic to sanitize or validate the content of the
AGENTS.mdfile to prevent embedded instructions from being executed by the agent.
Audit Metadata