ory-build-agent

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a framework for agents to audit and gate tool calls by passing tool arguments and results to the Ory platform. This creates an ingestion surface where untrusted data from tool executions is processed by the authorization logic.\n
  • Ingestion points: The toolArgs parameter in the gateTool function and the output parameter in the complete function within SKILL.md.\n
  • Boundary markers: The provided integration snippets do not implement specific delimiters or 'ignore' instructions for the data being passed to the auditing functions.\n
  • Capability inventory: The integration performs network requests to Ory identity and permission services to verify authorization status.\n
  • Sanitization: No explicit data sanitization or validation of tool inputs/outputs is shown in the snippets, as the processing logic is deferred to the @ory/argus library.\n- [EXTERNAL_DOWNLOADS]: The skill directs users to install the @ory/argus package using npm install. This is the official integration library provided by the vendor for adding security capabilities to agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:37 AM