simplify-code

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands such as git diff to identify code changes and executes project-specific test runners and linters to verify fixes.
  • [PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs, which represents an indirect prompt injection surface.
  • Ingestion points: git diff output in SKILL.md.
  • Boundary markers: Absent; the diff is passed directly to sub-agents without delimiters or warnings against embedded instructions.
  • Capability inventory: File-write capabilities and terminal command execution (tests/lint) in Phase 3 of SKILL.md.
  • Sanitization: None; the skill relies on its internal risk categorization (SAFE/CAREFUL/RISKY) and human review requirements for higher-risk changes to mitigate malicious suggestions.
  • [SAFE]: The skill's behavior is consistent with its stated purpose as a local code maintenance tool. No evidence of data exfiltration, obfuscation, or unauthorized access was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:32 AM
Security Audit — agent-trust-hub — simplify-code