research-explorer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to fetch and synthesize data from external, untrusted web sources. Ingestion points: Research activities defined in Phase 1 (Scoped Search) of SKILL.md. Boundary markers: Absent; there are no specific instructions to the agent to disregard commands embedded within the retrieved research data. Capability inventory: The skill is instructional only and does not possess or invoke dangerous system capabilities like local file writing or subprocess execution. Sanitization: Absent; no sanitization or filtering of external data is specified before processing.
- [No Code] (SAFE): The skill consists entirely of markdown instructions and does not ship with any executable scripts, binaries, or package manifest files.
Audit Metadata