doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources, which presents a risk of indirect prompt injection where malicious instructions embedded in the data could influence the agent's behavior.
- Ingestion points: File
SKILL.mddescribes gathering context from 'team channels', 'shared documents', and cloud services like 'Slack, Teams, Google Drive, SharePoint'. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard potential instructions found within the ingested data.
- Capability inventory: The agent has the ability to write to the file system using
create_fileand modify content usingstr_replace. - Sanitization: No sanitization, validation, or filtering of external data is defined before the information is integrated into the workflow.
Audit Metadata