fittings-fec-candidate-search

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a JavaScript client utility from the vendor's domain at fittings.sh/skill/call.mjs.
  • [REMOTE_CODE_EXECUTION]: Instructs the agent to execute the downloaded script using node to interact with the API endpoints.
  • [CREDENTIALS_UNSAFE]: Uses the FITTINGS_PRIVATE_KEY environment variable to store a blockchain private key used for payment settlement on the Base network.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting data from the external FEC API via the fittings.sh gateway.
  • Ingestion points: Data returned from the fec.candidate-search endpoint.
  • Boundary markers: No delimiters or instructions to ignore embedded content are present in the documentation.
  • Capability inventory: The skill uses curl for data fetching and node for executing downloaded logic.
  • Sanitization: There is no mention of filtering or sanitizing the data received from the external API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:32 PM