find-security-vulnerabilities-in-code
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
strixCLI tool to perform security analysis on source code. Commands include scanning local directories (strix -n -t ./) and remote GitHub repositories (strix -n -t https://github.com/org/app). This is the intended purpose of the skill and aligns with the vendor's provided documentation. - [INDIRECT_PROMPT_INJECTION]: This skill has an inherent attack surface for indirect prompt injection as it is designed to ingest and process untrusted data in the form of third-party source code and remote repositories.
- Ingestion points: Untrusted data enters the agent context through the codebase paths or repository URLs provided to the
strixtool inSKILL.md. - Boundary markers: No explicit boundary markers or 'ignore' instructions for the processed code are present in the skill instructions.
- Capability inventory: The skill executes the
strixshell command to perform its analysis. - Sanitization: There is no mention of sanitization or filtering of the ingested source code before processing.
- Ingestion points: Untrusted data enters the agent context through the codebase paths or repository URLs provided to the
Audit Metadata