ai-regression-testing
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands such as 'bun test' and 'bun run typecheck' to verify test outcomes and code correctness within the user's project environment.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it incorporates external data like bug reports and code diffs into its decision-making process for writing and running tests.
- Ingestion points: Processes external bug reports and code diffs as primary inputs for test generation (SKILL.md).
- Boundary markers: Lacks explicit delimiters or instructions for separating external input from internal task logic.
- Capability inventory: The agent can modify local files and execute shell commands based on the context of the testing task (SKILL.md).
- Sanitization: No visible mechanisms for sanitizing or escaping the content of processed diffs or reports are specified.
Audit Metadata