consolidate-test-suites
Pass
Audited by Gen Agent Trust Hub on May 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform local command execution for the purpose of code verification and testing.
- Evidence:
SKILL.mdcontains instructions to "Run the narrowest relevant test target first" and "Run required typecheck, build, or lint steps for touched code." - [PROMPT_INJECTION]: The skill operates on local source code and test files, which represents a potential surface for indirect prompt injection.
- Ingestion points: The agent reads and searches existing code and test files as part of its decision logic (
SKILL.md). - Boundary markers: Not present.
- Capability inventory: The skill can execute shell commands for testing, linting, and building (
SKILL.md). - Sanitization: None identified.
Audit Metadata