sumsub-manage-webhooks

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is well-designed with security in mind and contains no malicious code or instructions. It includes validation logic to ensure users do not inadvertently configure webhooks with unreachable local targets.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses (webhook configurations from Sumsub). While this represents a potential injection surface, the risk is mitigated by using rigid JSON parsing and specific field extraction in formatting scripts (e.g., fmt_list and manage_webhooks.sh logic) rather than raw interpolation of external content into the agent prompt.
  • [CREDENTIALS_UNSAFE]: The skill follows secure credential management practices by using environment variables. It additionally implements a proactive redaction step in the get command to ensure that webhook secrets returned by the API are not displayed in the conversation history.
  • [DATA_EXFILTRATION]: Network operations are restricted to the official vendor domain (api.sumsub.com). No unauthorized data exfiltration patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:35 PM
Security Audit — agent-trust-hub — sumsub-manage-webhooks