skills/coder/xum/deep-review/Gen Agent Trust Hub

deep-review

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted input from git diffs, which could contain instructions designed to bias the review process.
  • Ingestion points: The agent reads git diff output and file contents as described in SKILL.md.
  • Boundary markers: No explicit delimiters are used to isolate untrusted code from the agent's instructions.
  • Capability inventory: The skill uses sub-agents for analysis and reporting but does not perform network operations or unauthorized file writes.
  • Sanitization: The skill does not implement specific sanitization or filtering of the code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:47 PM
Security Audit — agent-trust-hub — deep-review