testing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides philosophical and practical guidance for software testing, emphasizing experimental validity and information gain over simple metric-chasing.
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and analyzing external project files, which constitutes a surface for indirect prompt injection. This is a functional requirement for the testing domain.
- Ingestion points: The skill directs the agent to read current code, behavior rules, callers, tests, and failure history in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided.
- Capability inventory: The skill utilizes shell execution for running project-specific CI commands and test checks as described in
SKILL.md. - Sanitization: No specific sanitization methods for ingested code are specified.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute project-specific test commands and CI suites. This is a primary function of the testing skill and is managed within the development context.
Audit Metadata