extract
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided code through the
$ARGUMENTSvariable, creating a surface for instructions embedded in source code to influence the agent. - Ingestion points: Data enters the context via the
$ARGUMENTSplaceholder inSKILL.md. - Boundary markers: Absent; the skill does not define delimiters for the input data.
- Capability inventory: Instructions include creating files and modifying existing ones ("Update every call-site").
- Sanitization: Absent; the skill does not specify any validation or filtering for the input code.
Audit Metadata