doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill establishes a multi-stage procedural workflow for document creation, focusing on collaborative context gathering and refinement.
  • [PROMPT_INJECTION]: The workflow includes ingestion of untrusted data from documents and messaging platforms, creating a surface for indirect prompt injection.
  • Ingestion points: Shared document links, files, and messaging threads (Slack, Teams) in Stage 1 of SKILL.md.
  • Boundary markers: None identified in the instructional text.
  • Capability inventory: The skill uses create_file and str_replace for document management in SKILL.md.
  • Sanitization: No specific content sanitization or validation logic is defined.
  • [SAFE]: References and adapts methodologies from a well-known technology provider's public repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 02:21 PM