sumsub-manage-applicant-tags

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and displays external data from Sumsub applicant profiles (such as names and existing tags) which are controlled by users outside the agent's immediate environment. This data is placed into the agent's context without sanitization.
  • Ingestion points: The read_back function in scripts/manage_applicant_tags.sh parses JSON data from the GET /resources/applicants/{applicantId}/one endpoint.
  • Boundary markers: Applicant data is printed directly to the context without delimiters or instructions for the agent to ignore potentially malicious embedded content.
  • Capability inventory: The skill uses the Bash tool to execute API requests, sign payloads using OpenSSL, and process JSON with Python. It also has Write permissions.
  • Sanitization: No sanitization or filtering is performed on the applicant-supplied strings (like names or tags) before they are surfaced to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:35 PM
Security Audit — agent-trust-hub — sumsub-manage-applicant-tags