skills/felixgeelhaar/skills/ai-expert/Gen Agent Trust Hub

ai-expert

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and interpret data from external websites, creating a potential vector for indirect prompt injection where adversarial content on a webpage could influence agent behavior.
  • Ingestion points: The skill retrieves external data using the WebSearch, WebFetch, and mcp__scout toolsets as specified in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or specific guidance to the agent to treat retrieved web content as untrusted data distinct from its primary instructions.
  • Capability inventory: The skill possesses powerful capabilities including project-wide file reading (Read, Glob, Grep) and network communication (WebSearch, WebFetch), which increases the potential impact of a successful injection.
  • Sanitization: There are no explicit requirements in the skill definition for validating, filtering, or escaping content fetched from remote URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:20 AM
Security Audit — agent-trust-hub — ai-expert