simplify-all
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external file content which acts as an untrusted ingestion point.\n- Ingestion points: Code and documentation files within the scope provided by the user are passed to multiple review agents (SKILL.md, Step 1).\n- Boundary markers: The instructions do not define boundary markers or include specific instructions to disregard commands or instructions embedded within the files being simplified.\n- Capability inventory: The skill has the capability to orchestrate multiple agents and aggregate findings to apply fixes, which involves file writing or modification tools (SKILL.md, Step 2).\n- Sanitization: No validation or sanitization of the ingested content is specified before it is processed by the review agents.
Audit Metadata