skills/caidanw/skills/cleanup-swift/Gen Agent Trust Hub

cleanup-swift

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes Swift source files modified during the session, which serves as a potential vector for indirect prompt injection.
  • Ingestion points: Files identified via git session history (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Proposing code edits and reading session files.
  • Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill utilizes git commands ('git status', 'git diff') to identify the relevant files for review. These are standard development tools used for their intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:12 PM
Security Audit — agent-trust-hub — cleanup-swift