serverchan
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs outbound network operations to a non-whitelisted third-party domain.
- Evidence: In
scripts/send.py, the script constructs a POST request tohttps://{user_id}.push.ft07.com/send/{key}.sendto transmit the notification payload. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data for notification delivery.
- Ingestion points: The script
scripts/send.pyacceptstitleanddesp(description) via command-line arguments (sys.argv). - Boundary markers: None identified; the payload is interpolated directly into the request data.
- Capability inventory: The skill has outbound network POST capabilities via the
urllib.requestmodule. - Sanitization: The data is URL-encoded for transport, but there is no validation or sanitization of the content to prevent the transmission of malicious instructions or sensitive information handled by the agent.
Audit Metadata