north-star-check

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill is a set of workflow instructions for game design audits and drift detection.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and quote external project documentation, which represents an ingestion surface for untrusted data.
  • Ingestion points: The agent reads the project's North Star document and docs/moments.md.
  • Boundary markers: No specific delimiters or sanitization instructions are defined to separate the document content from the agent's instructions.
  • Capability inventory: The skill does not utilize any executable tools, shell commands, network operations, or file-write capabilities.
  • Sanitization: There is no filtering or validation of the content read from the external documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 01:48 PM