external-context
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it is designed to ingest and summarize untrusted content from the public internet.
- Ingestion points: External data enters the agent context through the WebSearch and WebFetch tools utilized by the parallel document-specialist subagents.
- Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious instructions embedded within the fetched documentation.
- Capability inventory: The skill can programmatically spawn subagents using the Task tool to perform further actions based on search results.
- Sanitization: No sanitization, filtering, or validation of the retrieved web content is specified before the synthesis of the final results.
Audit Metadata