doc-research
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Vulnerability surface for indirect prompt injection through external data ingestion.\n
- Ingestion points: Untrusted content is retrieved from the internet using
WebSearchand thecloudflare-browserplugin (get_url_markdown).\n - Boundary markers: The workflow lacks explicit delimiters or 'ignore embedded instructions' warnings for the fetched content.\n
- Capability inventory: The agent has access to the
Bashtool (configured for the internalc7skill) and network search tools.\n - Sanitization: No sanitization or validation of the retrieved markdown is performed before it is processed by the agent.
Audit Metadata