agentsmd-claudemd-generator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from existing repository documentation to generate project-specific guidelines, creating a surface for potential injection.
- Ingestion points: Documentation files such as
README.mdandCONTRIBUTING.mdare analyzed during Phase 1 to provide context for the generated instructions. - Boundary markers: The skill lacks explicit instructions or delimiters that would direct the agent to ignore malicious instructions embedded within the source files being analyzed.
- Capability inventory: The skill has
WriteandEditpermissions, which it uses to create the finalAGENTS.mdandCLAUDE.mdguidelines. - Sanitization: There is no evidence of filtering or validation performed on the ingested content before it is incorporated into the output files.
Audit Metadata