code-review

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tools including git, gh (GitHub CLI), and pnpm to perform code analysis, fetch repository history, and run build/type-check validations. These are routine operations within a software development environment.
  • [COMMAND_EXECUTION]: Interacts with the bd (Beads) CLI utility to create and update tasks. This tool is identified as a vendor-specific resource for task management and its usage is consistent with the skill's purpose.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes external code content which represents a potential attack surface where malicious instructions could be embedded in code comments or PR descriptions.
  • Ingestion points: Code diffs and commit logs ingested through git diff and gh pr diff commands.
  • Boundary markers: None identified; code content is analyzed directly within the session context without specific delimiters.
  • Capability inventory: Execution of build scripts (pnpm build), task creation via CLI (bd), and file system writes for report generation.
  • Sanitization: No sanitization or escaping of the ingested code content is specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:11 PM
Security Audit — agent-trust-hub — code-review