travel-guide

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or direct prompt injections were detected in the skill instructions.
  • [NO_CODE] (SAFE): The skill consists exclusively of markdown instructions and tool definitions; no executable code or external package dependencies are present.
  • [Indirect Prompt Injection] (SAFE): The skill ingests untrusted data from web searches to identify attractions. However, the risk is negligible because the agent's capabilities are restricted to information retrieval and text generation. Evidence: 1. Ingestion point: internet_search (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Rail ticket queries, weather, and map searches (all informational). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:56 AM