content-matrix
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external data from local files without explicit sanitization or boundaries.
- Ingestion points: The skill reads
about-me.mdandvoice.mdfrom the user's project to customize the content generation (Step 1). - Boundary markers: There are no delimiters or specific instructions provided to the agent to disregard potential instructions embedded within those files.
- Capability inventory: The skill is limited to text generation and markdown table creation; it does not utilize shell execution, network access, or file-writing tools.
- Sanitization: No input validation or content filtering is performed on the data retrieved from the local files.
Audit Metadata