skills/astro-han/skills/shape/Gen Agent Trust Hub

shape

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill establishes a safe, human-in-the-loop framework for decision-making that prioritizes user feedback and consensus before any action is taken.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill instructs the agent to look up facts in the filesystem, tools, or available sources (SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore commands embedded in the external data sources.
  • Capability inventory: The skill allows for environment data lookups and plan synthesis, but mandates a user confirmation checkpoint before the agent acts on the results.
  • Sanitization: No explicit sanitization or input validation for external data is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — shape