investoday

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits the user's INVESTODAY_API_KEY to the external domain data-api.investoday.net via HTTPS headers. While this is the intended mechanism for authentication, it involves sending secrets to a domain not on the pre-approved list.
  • [EXTERNAL_DOWNLOADS]: The skill fetches financial data from the remote endpoint https://data-api.investoday.net/data/cloud/*.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from an external API (data-api.investoday.net) and prints it directly to the console for the agent to process. * Ingestion points: scripts/call_api.py fetches data from the API and prints the JSON response. * Boundary markers: Absent; there are no delimiters wrapping the API output to signal it as untrusted data. * Capability inventory: The script uses the requests library for network communication but does not have file-write or shell execution capabilities. * Sanitization: Absent; the API response is printed verbatim without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — investoday