doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from potentially untrusted external sources, creating a surface for indirect prompt injection.
- Ingestion points: External data is brought into the agent's context through file uploads, shared document links, and integrations with messaging platforms (Slack, Teams) or cloud storage (Google Drive, SharePoint, MCP servers) mentioned in Stage 1.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing content fetched from external sources.
- Capability inventory: The skill uses tools to create and modify the file system (
create_file,str_replace) and facilitates the invocation of sub-agents to process the drafted content in Stage 3. - Sanitization: There are no explicit instructions to sanitize, escape, or validate the data pulled from external integrations before it is used to influence the document's structure or content.
Audit Metadata