review

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically git diff origin/main...HEAD, to extract code changes for the review process.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the repository (code changes and documentation) which presents an indirect prompt injection surface where malicious instructions in the code could influence the agent.
  • Ingestion points: Git diff output, spec files, plan files, AGENTS.md, and CLAUDE.md (specified in SKILL.md).
  • Boundary markers: Absent; the skill does not use delimiters to isolate untrusted data from instructions.
  • Capability inventory: The skill has the ability to execute shell commands (git diff) and spawn specialized subagents (anti-overeng-reviewer).
  • Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 11:49 PM