scout
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from the public web, which introduces a surface for indirect prompt injection.
- Ingestion points: The skill spawns a research subagent that reads the body content of external URLs discovered during searches (Phase 2).
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to treat fetched data as untrusted text to prevent the subagent from following instructions embedded in the source material.
- Capability inventory: The subagent's findings are synthesized into reports that can be saved to the agent's local scratchpad directory (Phase 3).
- Sanitization: There are no specific instructions to sanitize or escape web content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill is designed to interact with external web resources for research purposes.
- Evidence: The workflow involves autonomous exploration of technical documentation, RFCs, and engineering blogs from industry-standard organizations like Stripe, Netflix, and Cloudflare to identify production archetypes.
Audit Metadata