simplify
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data that could influence the behavior of the simplification subagent.
- Ingestion points: The skill ingests user input via the $ARGUMENTS variable and file content or names identified through git diff or git status (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or safety markers to isolate user/file content from the subagent's task instructions.
- Capability inventory: The cdd-code-simplifier subagent possesses the capability to modify project source code based on its evaluation.
- Sanitization: No sanitization, filtering, or validation is applied to the ingested content before it is processed by the subagent.
Audit Metadata