doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill defines a procedural workflow for collaborative writing. It uses standard tool calls like create_file and str_replace for their intended purposes and manages external context via recognized integration patterns.
  • [PROMPT_INJECTION]: Analyzed for potential indirect prompt injection surface due to external data processing.
  • Ingestion points: The skill ingests data from external integrations (Slack, Teams, Google Drive, SharePoint), user-provided files, and shared document links during the 'Context Gathering' stage in SKILL.md.
  • Boundary markers: The instructions do not include explicit delimiters or instructions for the agent to ignore potentially malicious embedded commands within the ingested text.
  • Capability inventory: The skill uses the create_file and str_replace tools to create and modify document artifacts based on the gathered context.
  • Sanitization: There is no evidence of automated sanitization or validation for the content pulled from external integrations before it is used in drafting.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:28 AM