codex-skills-index
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation and metadata. There are no executable files, tool definitions, or automated actions that would run in the agent's environment.
- [SAFE]: The skill explicitly outlines safety guardrails, specifically advising against medical diagnosis and recommending professional consultation for physical symptoms. It defines a structured telemetry and contract system to ensure compliance and safety across related AI skills.
- [PROMPT_INJECTION]: The skill describes an architecture that ingests untrusted user data via chat flows and plan generation APIs, creating a surface for indirect prompt injection. However, the skill itself is documentation-only and includes instructions for validating payloads against schemas to mitigate risks. [Ingestion points]: v0/app/api/chat/route.ts, v0/app/api/generate-plan/route.ts; [Boundary markers]: Payloads are validated against contracts.md schemas; [Capability inventory]: None; [Sanitization]: Not implemented in this index.
Audit Metadata