weather-maps
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions are standard for an AI agent and do not contain any bypass attempts, role-play overrides, or instructions to ignore safety guidelines.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.
- Obfuscation (SAFE): The content is clear and uses no encoding, hidden characters, or homoglyphs.
- Unverifiable Dependencies & RCE (SAFE): No external packages are requested and no remote script execution is present.
- Privilege Escalation (SAFE): No commands for elevating privileges or modifying system files were found.
- Indirect Prompt Injection (LOW): While the skill processes user input (city names) for a tool call, this is the intended functionality of a weather skill and poses no significant risk in this context.
- Ingestion points: User city names are passed to the
maps_weathertool. - Boundary markers: None present.
- Capability inventory: Limited to the
maps_weathertool call. - Sanitization: None observed in the prompt instructions.
Audit Metadata