finnhub

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the @membranehq/cli package from npm, which is the official command-line interface provided by the vendor.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to handle authentication, manage connections, and execute actions against the Finnhub API.
  • [PROMPT_INJECTION]: The skill retrieves and processes external financial data, presenting a surface for indirect prompt injection. (1) Ingestion points: Market news, company profiles, and stock symbols retrieved from the Finnhub API as described in SKILL.md. (2) Boundary markers: Absent; the skill documentation does not provide specific delimiters or instructions to isolate external data from agent logic. (3) Capability inventory: The skill can execute pre-defined actions and arbitrary proxy requests via the membrane CLI (e.g., membrane action run, membrane request). (4) Sanitization: Absent; no evidence of sanitization or validation of the external API responses is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:27 PM