analyze-tests
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using tools like
uv,rg(ripgrep),bun, andcargoto run tests and search through the project's source code. These are standard development tools and are used here for analytical purposes. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data (the user's project files) and executes search patterns against them, creating a surface for indirect prompt injection if those files contain malicious instructions meant to be interpreted by the agent.
- Ingestion points: Project source files (Python, JavaScript, TypeScript) and test coverage output files.
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the analyzed files.
- Capability inventory: Shell command execution (
uv,rg,bun,cargo, and native project test commands). - Sanitization: Absent; no filtering or sanitization of the file content is performed before processing.
Audit Metadata