convex-authz
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npx tsc --noEmitto verify that automated authorization hardening does not introduce syntax or type errors, ensuring the integrity of the application after modification.\n- [PROMPT_INJECTION]: The skill processes user-provided source code files (convex/**/*.ts), which represents an indirect prompt injection surface where malicious instructions could be embedded in comments or strings. However, the skill mitigates this by using objective, regex-based scanning to guide its actions.\n - Ingestion points: Project source files within the
convex/directory.\n - Boundary markers: None identified in the instruction set.\n
- Capability inventory: Local file modification and execution of
npx tsc.\n - Sanitization: None; the skill performs direct inspection of raw code content.
Audit Metadata