unit-test-generator
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it reads and processes external source code files which may contain adversarial instructions.
- Ingestion points: Untrusted source code files are ingested into the agent's context through the
Readtool as part of the analysis step (SKILL.md). - Boundary markers: The skill instructions do not specify any delimiters or instructions to the agent to ignore potentially malicious embedded content within the analyzed source files.
- Capability inventory: The agent has access to powerful tools including
Write(to create test files) andBash(to execute them), which could be misused if the agent is influenced by malicious instructions in the code it analyzes (SKILL.md). - Sanitization: No validation, escaping, or filtering of the source code content is mentioned before it is processed by the agent.
Audit Metadata