writing-unit-test

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references a dependency on an external repository (github.com/mattpocock/skills) and suggests an installation command (npx skills add). This is presented as an informational setup step for the user and does not involve automated or hidden execution by the agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided code snippets to assist in test generation, which is its primary purpose.
  • Ingestion points: User-provided functions and components are processed by the agent as described in SKILL.md.
  • Boundary markers: No explicit delimiter or sanitization instructions are present in the skill text.
  • Capability inventory: The skill contains no executable code, subprocess calls, or file-system writing capabilities beyond the agent's default behavior.
  • Sanitization: No specific input sanitization is defined, relying on the underlying model's safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 03:45 AM
Security Audit — agent-trust-hub — writing-unit-test