code-review

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the skill-gate --strict command at the repository root. This is intended to run automated checks such as formatting, linting, and security scans (SCA/SAST).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, specifically source code, diffs, and PR descriptions, which could contain adversarial content intended to override agent instructions.
  • Ingestion points: User-provided code, diffs, PRs, and design documents specified in the instructions.
  • Boundary markers: The skill does not define explicit delimiters or instructions to treat the ingested code as untrusted data.
  • Capability inventory: The agent has the capability to execute shell commands (skill-gate) and read files throughout the repository.
  • Sanitization: No input validation or sanitization steps are defined before the agent analyzes the provided code changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:14 PM
Security Audit — agent-trust-hub — code-review