refine-tests
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data (source code and test files) that may contain malicious instructions or code meant to influence the agent's behavior or exploit its capabilities.
- Ingestion points: The skill inventories all test files (SKILL.md Step 2) and performs deep-reads of source and test file pairs (SKILL.md Step 4).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the ingested code as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill instructs the agent to execute shell commands to run tests, linters, and typecheckers on the modified code (SKILL.md Step 7).
- Sanitization: The skill lacks mechanisms to sanitize or validate the content of the files before they are processed or executed.
- [COMMAND_EXECUTION]: The skill's core functionality requires the execution of arbitrary shell commands to run test runners and verification tools. While this is necessary for its purpose, it represents a significant capability that could be misused if the agent is influenced by malicious content in the files it audits.
Audit Metadata