high-value-tests
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted external data and has execution capabilities.
- Ingestion points: Reads repository code changes, existing test files, and repository guidance documentation.
- Boundary markers: None identified; the skill does not use delimiters or instructions to ignore embedded commands in the data it processes.
- Capability inventory: Instructs the agent to execute shell commands for running test suites.
- Sanitization: No validation or sanitization of the input files or the generated test commands is specified.
- [COMMAND_EXECUTION]: The skill explicitly directs the agent to run test commands. While this is the primary purpose of the skill, the execution of commands in an environment where untrusted code is being processed constitutes a security risk.
Audit Metadata