convex-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data that could influence agent behavior.
- Ingestion points: The skill reads deployment logs (via a
logstool) and analyzes function source code (SKILL.md Step 3) to identify the root causes of performance issues. - Boundary markers: The instructions do not specify the use of delimiters or clear "ignore embedded instructions" warnings when processing the contents of logs or source code.
- Capability inventory: The skill has the ability to read deployment metadata, read source code, and offer to apply code fixes to the user's environment (SKILL.md Step 5).
- Sanitization: There is no mention of sanitizing, escaping, or filtering the ingested code or log content before processing.
Audit Metadata