code-review

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as git diff and grep to retrieve and inspect code changes across various effort levels (SKILL.md, low.md, medium.md, high.md, xhigh.md, max.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from git diffs, which may contain malicious instructions designed to hijack the agent's reasoning or output format.
  • Ingestion points: The agent gathers unified diffs using git diff commands in Phase 0 of the review process.
  • Boundary markers: No explicit delimiters (like XML tags or specific markdown blocks) or instructions to ignore embedded commands within the diff are provided.
  • Capability inventory: The skill utilizes git diff, grep, and an Agent tool capable of sub-task execution.
  • Sanitization: No sanitization, escaping, or validation of the diff content is performed before the agent analyzes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:30 PM
Security Audit — agent-trust-hub — code-review