convex-conventions
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional guidelines for Convex backend development and architectural patterns. It does not contain malicious code, obfuscation, or unauthorized data access patterns.\n- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to verify APIs against external Convex documentation and release notes, creating an ingestion surface for external content.\n
- Ingestion points: External "live Convex docs" and "release notes" mentioned in SKILL.md.\n
- Boundary markers: The instructions specify that "Live docs win over this skill," providing a hierarchy for information authority.\n
- Capability inventory: The skill is intended for code scaffolding, review, and refactoring tasks.\n
- Sanitization: No specific sanitization or filtering of documentation content is described.
Audit Metadata