deslop
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to process untrusted data (the output of
git diff) and perform actions (modifying files) based on that content. - Ingestion points: Untrusted data enters via the
git diff main...HEADcommand output in the process step. - Boundary markers: Absent; there are no instructions to ignore or delimit instructions found within the diff.
- Capability inventory: The skill requires the ability to read the file system and write/modify files to "remove identified slop".
- Sanitization: Absent; the agent is not instructed to sanitize the content of the diff before processing it.
Audit Metadata