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
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:29 PM
Security Audit — agent-trust-hub — deslop