insane-research-query

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local configuration script found at "${CLAUDE_PLUGIN_ROOT}/setup/setup.sh" during its initial run to prepare the environment.
  • [COMMAND_EXECUTION]: The skill saves the generated research queries to the local file system within the "RESEARCH/queries/" directory.
  • [PROMPT_INJECTION]: The skill processes user-supplied research topics and requirements to generate search keywords and research briefs, which constitutes an indirect prompt injection surface.
  • Ingestion points: User-provided research topic, geographic scope, and source quality selections gathered via the AskUserQuestion tool in Phase 1 and Phase 2.
  • Boundary markers: The instructions do not define specific delimiters to isolate user-provided data within the generated JSON or markdown structures.
  • Capability inventory: The skill can execute local bash commands and perform file system writes.
  • Sanitization: User inputs are used directly to generate keywords and descriptions without explicit validation or sanitization rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 06:47 AM
Security Audit — agent-trust-hub — insane-research-query