test
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from test outputs and source code to identify failures and propose fixes. This creates a surface where the agent might interpret data as instructions.
- Ingestion points: Test output strings and the content of failing test files are read into the agent's context for analysis (SKILL.md).
- Boundary markers: No specific delimiters or warnings are used to tell the agent to ignore instructions embedded in the test data.
- Capability inventory: The skill utilizes Bash for command execution and Read/Write/Edit tools for file manipulation.
- Sanitization: There is no evidence of sanitization or filtering for the external data ingested from test results.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute testing frameworks like Vitest, Jest, and Playwright. It interpolates arguments directly into shell commands (e.g.,
npm run test -- $ARGUMENTS), which is an expected part of its testing functionality but requires careful handling of input.
Audit Metadata