skills/citypaul/.dotfiles/find-gaps/Gen Agent Trust Hub

find-gaps

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured, human-in-the-loop process for artifact review. It contains no executable code, remote network operations, or sensitive file access.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted user-provided artifacts and generates updates based on them. However, the risk is mitigated by explicit instructions to confirm every change with the user.
  • Ingestion points: User-provided plans, specs, and design mocks (SKILL.md).
  • Boundary markers: None specified in the instructions for separating artifact content from agent instructions.
  • Capability inventory: The skill is instructed to write confirmed updates to the source of truth (file, canvas, or document) and uses the AskUserQuestion tool for interaction.
  • Sanitization: Relies on a conversational loop and a human reviewer to verify and confirm all proposed artifact updates before they are written to the destination.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 04:25 PM
Security Audit — agent-trust-hub — find-gaps