skills/shpigford/skills/but-for-real/Gen Agent Trust Hub

but-for-real

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions direct the agent to utilize standard CLI tools such as git diff, compilers, and test suites for validating changes before submission. These are legitimate development workflows.
  • [PROMPT_INJECTION]: The skill employs an aggressive, persona-driven tone to enforce strict adherence to user requirements. This use of language is intended to reduce errors and does not target the subversion of AI safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 10:53 AM