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
Risk Level
SAFE
Analyzed
Aug 17, 2026, 05:54 AM
Security Audit — agent-trust-hub — authoring-tests