writing-staffing

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized behaviors were detected in the skill files.
  • [COMMAND_EXECUTION]: The skill utilizes the meridian CLI for spawning agents and managing sessions, which is the intended functionality for this orchestration framework.
  • [EXTERNAL_DOWNLOADS]: The researcher and wiki-editor agents are described as having web access to support fact-checking and context gathering.
  • [PROMPT_INJECTION]: The skill processes untrusted data from web sources (resources/researchers.md) and user drafts (resources/critics.md), representing an indirect prompt injection surface. No explicit boundary markers or sanitization steps are documented; however, the agent's capabilities are limited to the writing project's scope (meridian spawn and file writes), and the modular architecture provides inherent isolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 01:14 AM