doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external, potentially untrusted sources, which creates a surface for indirect prompt injection.
- Ingestion points: The workflow instructions suggest reading context from Slack, Microsoft Teams, Google Drive, SharePoint, and user-provided document links (SKILL.md).
- Boundary markers: The skill does not implement delimiters or safety instructions to prevent the agent from obeying commands embedded within the external content it reads.
- Capability inventory: The agent is instructed to use
create_fileandstr_replacetools to modify the workspace and can invoke sub-agents for automated 'Reader Testing' (SKILL.md). - Sanitization: There is no evidence of content sanitization or validation of data retrieved from external integrations before it is processed by the agent.
Audit Metadata