council-review-subagents

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill follows standard practices for local file manipulation and subagent orchestration.
  • [EXTERNAL_DOWNLOADS]: Mentions a public GitHub repository (karpathy/llm-council) for reference. No code is downloaded or executed from the remote source.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface where untrusted user input is processed by subagents. Ingestion points: The idea text and user context are read in Step 1 of SKILL.md. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used. Capability inventory: The skill can spawn general-purpose subagents and write assessment files to the local workspace. Sanitization: No sanitization or validation of the input text is performed before it is passed to the subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 07:17 PM
Security Audit — agent-trust-hub — council-review-subagents