extension-oql

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The ingestion tool (scripts/ingest.mjs) executes the icp command-line utility to communicate with the Internet Computer.
  • Evidence: The icpCall function (lines 186-210) uses node:child_process.execFile to invoke icp canister call with parameters for identity, network, and canister target.
  • Mitigation: The script validates canister identifiers using regex and escapes argument strings to mitigate injection risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill's function of exposing canister data to AI agents creates an indirect prompt injection attack surface.
  • Ingestion points: Data is queried through the OQL schema() and execute() endpoints exposed by the canister.
  • Boundary markers: Data is returned to the agent in structured JSON format.
  • Capability inventory: The agent can read all records defined as OQL entities by the canister developer.
  • Sanitization: The skill does not implement specific sanitization of the data values retrieved from the canister.
  • [EXTERNAL_DOWNLOADS]: The skill requires a Motoko package to be installed.
  • Evidence: SKILL.md provides instructions to run mops add caffeineai-oql@0.8.1.
  • Note: The package is a vendor-owned resource authored by caffeinelabs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 09:17 PM