fittings-nws-area-alerts
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a utility script from the vendor's domain at
https://fittings.sh/skill/call.mjsusingcurl. - [REMOTE_CODE_EXECUTION]: The skill instructs the agent to run the downloaded script (
call.mjs) using thenoderuntime. - [COMMAND_EXECUTION]: The skill uses shell commands, including
curl,jq, andnode, to download resources, query the catalog, and execute payments. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via external weather data.
- Ingestion points: Real-time National Weather Service alerts are retrieved from
https://fittings.sh/v1/nws/area-alertsand processed by the agent. - Boundary markers: There are no delimiters or instructions provided to the agent to treat the external data as untrusted or to ignore embedded instructions.
- Capability inventory: The agent has access to shell command execution (
node,curl) which could be targeted by a malicious payload in the alert data. - Sanitization: No validation or sanitization of the incoming alert content is performed before presentation to the agent.
Audit Metadata