fittings-nws-point-forecast

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include downloading a helper script directly from the vendor's domain. \n
  • Evidence: curl -sO https://fittings.sh/skill/call.mjs in SKILL.md.
  • [REMOTE_CODE_EXECUTION]: The skill directs the agent to execute a downloaded JavaScript file using the Node.js runtime. \n
  • Evidence: node call.mjs nws.point-forecast ... in SKILL.md.
  • [COMMAND_EXECUTION]: Shell commands such as curl and node are used to perform the skill's core functions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes weather data fetched from an external API, which serves as an ingestion point for untrusted content. \n
  • Ingestion points: GET request to https://fittings.sh/v1/nws/point-forecast. \n
  • Boundary markers: None specified. \n
  • Capability inventory: curl, node. \n
  • Sanitization: Not explicitly documented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:33 PM