requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git utilities (git rev-parse, git log, git diff) to determine commit ranges and generate code differences for the review subagent. These operations are confined to the local repository.
  • [PROMPT_INJECTION]: The code-reviewer.md template relies on variable interpolation for fields such as {BASE_SHA}, {HEAD_SHA}, and {DESCRIPTION}. This structure is susceptible to indirect prompt injection if the inputs are derived from untrusted project files or malicious commit descriptions. (1) Ingestion points: Variables within the code-reviewer.md template. (2) Boundary markers: None present to delineate input from instructions. (3) Capability inventory: The subagent executes git commands and provides qualitative code assessments. (4) Sanitization: The skill does not implement validation or escaping for the interpolated git hashes or text descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:42 AM
Security Audit — agent-trust-hub — requesting-code-review