toss-investment

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to run npx -y @nomadamas/k-skill@0 to fetch instructions and legal documentation. This targets the author's official CLI package on the public npm registry. Since '@nomadamas' is the identified vendor for this skill, this is considered standard vendor functionality and not a security risk.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill requires TOSSINVEST_CLIENT_ID and TOSSINVEST_CLIENT_SECRET environment variables. The instructions explicitly mandate that these credentials stay within the user's environment, are sent directly to the official API origin (https://openapi.tossinvest.com), and are masked in error logs. No evidence of credentials being sent to unauthorized third parties was found.
  • [COMMAND_EXECUTION]: The skill documentation includes examples of running npx commands. These are used for documentation retrieval and instruction generation, which is a common pattern for k-skill stubs and does not involve arbitrary command execution of untrusted input.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests financial data from the official Toss API. While this is a data ingestion surface, the skill is scoped to read-only operations and includes instructions to mask sensitive information and follow strict output boundaries, minimizing the risk of prompt injection from the API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 05:43 AM
Security Audit — agent-trust-hub — toss-investment