assertion-helper

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes code logic to generate test assertions, creating a surface where malicious instructions in the analyzed code could influence the agent's behavior.\n
  • Ingestion points: Logic, signatures, and input parameters passed to the assertion generation tool in SKILL.md.\n
  • Boundary markers: Lacks delimiters to distinguish between the instructions and the code being analyzed.\n
  • Capability inventory: Generates executable code for multiple frameworks. The skill itself is text-based but intended for a pipeline that may execute the result.\n
  • Sanitization: No input sanitization is demonstrated before data is placed into templates.\n- [DYNAMIC_EXECUTION]: The skill generates executable script content from templates at runtime based on user-provided logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:43 AM