deslop
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process code diffs introduced in a branch. If these diffs contain malicious instructions embedded in comments or strings, the agent might execute them while attempting to 'clean' the code.
- Ingestion points: The agent ingests untrusted code data by checking the diff against the 'main' branch (SKILL.md).
- Boundary markers: There are no explicit delimiters or boundary instructions to help the agent distinguish between the code data it is cleaning and the instructions it should follow.
- Capability inventory: The agent has the capability to read project files and modify them to remove identified content (SKILL.md).
- Sanitization: No sanitization or validation of the ingested code content is performed before the agent processes it for 'slop' detection.
Audit Metadata