unit-test-writer
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local source code files (e.g.,
cat src/module/feature.py) to analyze functionality and generate tests. This creates a surface for indirect prompt injection where malicious instructions embedded in the code being analyzed could influence the agent's behavior or output. - Ingestion points: Source code files read via the
catcommand in the 'Analyze Code to Test' section ofSKILL.md. - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded prompts in the ingested files.
- Capability inventory: The skill uses
Write,Edit, andBashtools, which could be abused if the agent is successfully injected. - Sanitization: Absent; the skill does not suggest any validation or filtering of the source code content before processing.
Audit Metadata