doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes 'create_file' and 'str_replace' tool calls to manage the iterative document drafting and editing process within the agent's environment.
  • [EXTERNAL_DOWNLOADS]: The workflow retrieves project context from various third-party platforms, including Slack, Microsoft Teams, Google Drive, and SharePoint, through the use of platform-native connectors and MCP servers.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes untrusted data from external sources.
  • Ingestion points: External content gathered from messaging channels (Slack, Teams) and shared document storage (Google Drive, SharePoint) during the Context Gathering stage.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are used when processing content from these external integrations.
  • Capability inventory: The skill has the ability to create and modify files ('create_file', 'str_replace') and invoke sub-agents for testing, which could be exploited if malicious instructions are present in the ingested data.
  • Sanitization: The skill does not perform explicit sanitization or validation of the content retrieved from external sources before incorporating it into the document drafting workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 05:06 PM
Security Audit — agent-trust-hub — doc-coauthoring