skills/mindmorass/reflex/web-research/Gen Agent Trust Hub

web-research

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted data from the web and stores it in a persistent knowledge base.
  • Ingestion points: Web search results retrieved via WebSearch and existing knowledge retrieved via qdrant-find (SKILL.md).
  • Boundary markers: Absent. The workflow does not define specific delimiters or instructions to ignore embedded commands within the harvested web content.
  • Capability inventory: The skill uses qdrant-find, WebSearch, and qdrant-store. It does not contain capabilities for arbitrary command execution (eval/exec) or sensitive file system access.
  • Sanitization: Absent. There is no evidence of content filtering or sanitization of the data before it is stored or processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM