agents-md-writer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content to influence the generation and modification of instruction files, which can be leveraged for indirect prompt injection.
- Ingestion points: The workflow instructs the agent to read and inventory repo-root files, nested instruction sources, package scripts, CI workflows, and project documentation (documented in steps 2 and 3 of SKILL.md).
- Boundary markers: There are no requirements in the instructions to use delimiters, tags, or 'ignore' prefixes when handling or interpolating data extracted from external repository files.
- Capability inventory: The skill possesses the capability to read any file within the repository and write or edit markdown files (AGENTS.md and tool-specific instructions).
- Sanitization: The instructions do not define any sanitization, escaping, or validation logic for the content read from scripts or documentation before it is used to justify or create new rules.
Audit Metadata