investigate
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via its research phase.\n
- Ingestion points:
WebSearchandWebFetchare used inprotocols/research.mdto collect data from the internet based on sub-problems.\n - Boundary markers: No delimiters or protective instructions are defined to isolate untrusted web content from the agent's internal logic.\n
- Capability inventory: The skill can write files to the local system (targeting
$THINKING_DIRinSKILL.md) and execute sub-agents using theTasktool.\n - Sanitization: External web content is synthesized into trade-off matrices and design decisions without validation or filtering.\n- [EXTERNAL_DOWNLOADS]: The skill performs automated data collection from external web services.\n
- The
Researchprotocol inprotocols/research.mdexplicitly instructs the agent to utilizeWebSearchandWebFetchto investigate solutions and patterns for identified technical challenges.
Audit Metadata