document
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted source code provided in the
targetargument, which creates a risk that instructions embedded in comments or code could influence the agent. - Ingestion points: The specific file, function, or component provided as the
targetargument inSKILL.md. - Boundary markers: No delimiters or instructions are specified to help the agent distinguish between the code to be documented and potential malicious instructions within that code.
- Capability inventory: The skill utilizes
Read,Edit, andWritetools as described in the 'Claude Code Integration' section, meaning a successful injection could lead to unauthorized file reads or writes. - Sanitization: The instructions do not describe any sanitization or validation steps for the input data before it is processed by the documentation engine.
Audit Metadata