verification-before-completion

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional, establishing a 'Gate Function' that requires the agent to run verification commands and review output before claiming tasks are done. It does not introduce any technical risks.
  • [NO_CODE]: There are no scripts, binaries, or automated tasks associated with this skill. It operates purely at the prompt/instruction level.
  • [EXTERNAL_DOWNLOADS]: References to the upstream repository (obra/superpowers) are for provenance and documentation purposes only; no code or content is downloaded or executed from these sources at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 01:13 PM
Security Audit — agent-trust-hub — verification-before-completion