skills/maxmurr/skills/writing-evals/Gen Agent Trust Hub

writing-evals

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: A potential injection pattern ('Ignore previous instructions') was detected in references/templates/classification.md. Upon review, this is a false positive as it is included as a sample adversarial test case in a code template, not as a command to the agent.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of standard development packages evalite and vitest from public registries. These are appropriate for the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill involves reading project source code and generating test files. This behavior is consistent with its role as a code generation and evaluation tool for developers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:45 AM