w-deslop

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code diffs (specifically identifying 'slop' such as comments and defensive noise). Maliciously crafted code or comments within the branch being analyzed could attempt to influence the agent's behavior through indirect injection.
  • Ingestion points: Git diff output comparing the current branch against main (SKILL.md).
  • Boundary markers: None specified to differentiate between data to be cleaned and instructions.
  • Capability inventory: File system write access (intended for removing code/comments).
  • Sanitization: No explicit sanitization or validation of the diff content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:00 AM
Security Audit — agent-trust-hub — w-deslop