sumsub-api-generic

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automatically downloads the Sumsub OpenAPI definition from https://api.sumsub.com/agents-openapi.json. This is a legitimate vendor resource used to provide the agent with current API documentation for endpoint discovery.\n- [DATA_EXFILTRATION]: The skill uses curl to send authenticated requests to api.sumsub.com using the SUMSUB_APP_TOKEN and SUMSUB_SECRET_KEY provided by the user in the environment. This represents the primary intended function of the skill and is constrained to the official service domain.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests data from external sources (the OpenAPI schema and API responses). Specifically:\n
  • Ingestion points: scripts/_schema_cache.py (OpenAPI schema) and scripts/sumsub_curl.sh (API responses).\n
  • Boundary markers: No explicit delimiters are used to wrap the external content.\n
  • Capability inventory: The skill can execute shell commands (Bash), perform network operations (curl), and write to the local cache.\n
  • Sanitization: The skill parses JSON data but does not perform content sanitization on the response text surfaced to the user.\n- [COMMAND_EXECUTION]: The skill executes provided Python and Bash scripts to manage the schema cache, search for endpoints, and perform API calls. These scripts are part of the skill package and perform standard utility tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:08 PM
Security Audit — agent-trust-hub — sumsub-api-generic