research-assistant
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data from external web sources.
- Ingestion points: Untrusted data enters the agent context via the
web_researchaction-set in the 'Gather Information' step. - Boundary markers: The instructions lack specific delimiters or warnings to ignore potentially malicious instructions embedded in the retrieved web content.
- Capability inventory: The skill is configured with
web_research(data retrieval) andfile_operations(potential data persistence) action-sets. - Sanitization: There is no evidence of content filtering, escaping, or validation of the information retrieved from external sources before it is processed by the agent.
Audit Metadata