portal

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a detailed reference guide and documentation set for the Subsquid Portal blockchain data API. No malicious patterns or security vulnerabilities were detected.
  • [COMMAND_EXECUTION]: Provides benign examples using curl, date, and jq to interact with the vendor's official API at portal.sqd.dev for tasks such as metadata verification and timestamp resolution.
  • [DATA_EXPOSURE]: Network operations are restricted to the vendor's domain (portal.sqd.dev) and well-known industry resources (4byte.directory, openchain.xyz) for legitimate data retrieval and signature verification.
  • [INDIRECT_PROMPT_INJECTION]: As a data-querying reference, the skill enables the agent to ingest blockchain data. While on-chain data is untrusted, the skill provides the structure for queries rather than performing unsafe processing, which is standard for the intended primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:33 PM
Security Audit — agent-trust-hub — portal