doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external content from shared documents and team channels, creating a surface for indirect prompt injection.
- Ingestion points: Data enters via info-dumps, linked documents, and team threads (Stage 1 and 3).
- Boundary markers: The instructions lack explicit delimiters or 'ignore' commands for the ingested content.
- Capability inventory: The skill uses tools like
create_file,str_replace, and sub-agent execution. - Sanitization: No sanitization or escaping of external content is specified.
Audit Metadata