fittings-drought-severity
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to download a JavaScript file (
call.mjs) from the vendor's infrastructure (fittings.sh) and execute it using Node.js to handle API requests and payments. - [EXTERNAL_DOWNLOADS]: Fetches executable code and service metadata from
https://fittings.sh/skill/call.mjsandhttps://fittings.sh/catalog/drought.severity. - [COMMAND_EXECUTION]: Utilizes shell commands (
curl,node) to fetch external scripts and run local code for interacting with the Drought Monitor API. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the
https://fittings.sh/v1/drought/severityendpoint, which could be a vector for indirect injection if the data source is compromised. - Ingestion points: API responses from the Drought Monitor severity endpoint described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the tool output as untrusted data.
- Capability inventory: The agent can execute downloaded scripts via Node.js and perform network requests.
- Sanitization: No sanitization or validation of the external API response is performed before processing.
Audit Metadata