doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes text from external sources such as shared documents and messaging platforms, which is inherent to its primary purpose of documentation co-authoring.
- Ingestion points: Processes content from Slack, Microsoft Teams, Google Drive, and SharePoint as specified in references/stage1-context.md.
- Boundary markers: None explicitly defined for ingested content.
- Capability inventory: Uses create_file and str_replace to manage documentation artifacts.
- Sanitization: Relies on iterative user review and does not specify automated sanitization.
Audit Metadata