review-llm-artifacts

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and reviews untrusted code from the repository.
  • Ingestion points: Code file names and contents gathered via git diff and find as described in Step 1.
  • Boundary markers: No explicit delimiters or boundary instructions are defined to prevent the agent from following instructions potentially embedded within the code being analyzed.
  • Capability inventory: The skill utilizes shell commands (git, find, mkdir, python3, jq), spawns parallel subagents via the Task tool, and writes analysis results to the local filesystem.
  • Sanitization: No sanitization or validation of the ingested code content is performed before it is processed by subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 03:32 AM
Security Audit — agent-trust-hub — review-llm-artifacts