doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a benign procedural workflow for guiding users through document creation. It relies on user-provided information and standard platform tools for drafting and editing text files.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process data from external sources like shared documents, messaging channels, and local files.
  • Ingestion points: Stage 1 instructions explicitly request context from shared links, uploaded files, and integrated team channels (SKILL.md).
  • Boundary markers: No delimiters or specific instructions are provided to the agent to treat external content as data rather than instructions.
  • Capability inventory: The skill utilizes file system modification capabilities (create_file, str_replace) and has the ability to spawn sub-agents for testing.
  • Sanitization: There is no evidence of content sanitization or validation for the ingested external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:34 PM
Security Audit — agent-trust-hub — doc-coauthoring