tidy
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from git branches and uncommitted changes, which serves as a significant attack surface for instructions embedded in data.
- Ingestion points: The instructions in
SKILL.mddirect the agent to process the branch's diff and uncommitted changes, which are external, untrusted sources. - Boundary markers: The skill lack explicit boundary markers or instructions to ignore natural language instructions that might be embedded within code comments or string literals in the files being tidied.
- Capability inventory: The skill possesses the capability to modify files ("Tidy all code the branch's diff touches"), which could be abused if the agent obeys instructions found within the code.
- Sanitization: There is no mention of sanitizing or filtering the ingested code to distinguish between code to be cleaned and potential malicious instructions.
Audit Metadata