authoring-tests
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides best practices and architectural patterns for various test types. No evidence of obfuscation, hardcoded credentials, or unauthorized network operations was found.
- [SAFE]: Referenced documentation paths are internal to the project directory, which is standard behavior for vendor-authored developer tooling.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it allows the agent to ingest external data for code generation and execution tasks.
- Ingestion points: Processes user-supplied test cases and reads local project documentation such as '@projects/site/src/docs/internal/guidelines/testing.md' (SKILL.md).
- Boundary markers: None identified to differentiate between documentation data and agent instructions.
- Capability inventory: The instructions call for the agent to write test files and execute test runners, involving file system writes and command execution (SKILL.md).
- Sanitization: No explicit sanitization, validation, or filtering mechanisms are defined for the documentation content processed.
Audit Metadata