acceptance-matrix
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and YAML configuration metadata. No executable scripts, binaries, or configuration for tool usage are included.
- [NO_CODE]: There are no scripts or executable files associated with this skill. It operates solely within the context of the agent's prompt instructions to generate text-based output.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external sources like specifications, tickets, and conversation history. While the surface exists, the risk is minimal as the output is static markdown documentation.
- Ingestion points: The skill reads supplied specs, plans, tickets, or conversations as described in SKILL.md.
- Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded instructions within the source data.
- Capability inventory: The skill only produces markdown text. No subprocess calls, exec/eval functions, file-writing, or network operations are present in any of the skill files.
- Sanitization: Absent; no sanitization or filtering of external content is specified.
Audit Metadata