strategy-expert

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill consists of high-quality instructional content for strategic analysis and uses standard tools for research.
  • [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection because it is designed to analyze external data retrieved via web tools. This is a functional requirement for competitive intelligence and is assessed as safe as there is no automated command execution based on the ingested content.
  • Ingestion points: Data from WebSearch, WebFetch, and scout-related tools (mcp__scout__navigate, mcp__scout__readable_text, mcp__scout__observe).
  • Boundary markers: None specified for separating external data from instructions.
  • Capability inventory: Read, Glob, Grep, WebSearch, WebFetch, mcp__scout__navigate, mcp__scout__readable_text, mcp__scout__observe.
  • Sanitization: No specific sanitization or filtering logic is included in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 04:01 PM
Security Audit — agent-trust-hub — strategy-expert