content-matrix
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses directive headers like "CRITICAL: Auto-start on load" and instructions such as "Do not summarise," which are patterns aimed at overriding the agent's default interaction protocols and response formatting.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data from user-controlled files and has the capability to write output to the file system, creating a vulnerability surface for indirect instructions.
- Ingestion points: The skill reads content from local files
about-me.mdandvoice.mdlocated in the agent's working directory. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the imported file content as potentially untrusted data.
- Capability inventory: The skill utilizes file system tools to write and save new markdown files based on the generated content matrix.
- Sanitization: The skill does not perform any sanitization or validation of the content extracted from the input files before processing it.
Audit Metadata