skills/ting-s515/skills/bdd-unit-test/Gen Agent Trust Hub

bdd-unit-test

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by design, as its core function involves processing user-provided source code.
  • Ingestion points: The skill reads user-specified file paths or code snippets to identify methods and logic (referenced in SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters for the agent to distinguish between code logic and potential natural language instructions embedded in comments or strings within the source files.
  • Capability inventory: The agent's capabilities in this skill are focused on code analysis and generating unit test files; no direct shell execution or external network access is requested based on the input.
  • Sanitization: The skill does not implement any validation or sanitization steps to filter out non-code instructions from the input data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:28 PM