convex-cost
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is focused on analyzing resource consumption metrics (bytes read, documents read) to provide cost transparency for Convex deployments. It includes a guardrail requiring explicit user confirmation before any metered actions are performed.
- [INDIRECT_PROMPT_INJECTION]: The skill handles data from external deployment insights which presents an attack surface for indirect instructions.
- Ingestion points: Retreives data from insights and tables tools (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters for retrieved metadata.
- Capability inventory: The skill has no capabilities for code execution, system modification, or network communication to third-party domains.
- Sanitization: No specific sanitization or filtering logic is mentioned for the processed metrics.
Audit Metadata