evaluate-connector

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external code for review, which is an attack surface for indirect prompt injection.\n
  • Ingestion points: The agent reads Python files and dependency lists from the user-provided connector directory.\n
  • Boundary markers: The instructions do not define specific delimiters for the ingested code content.\n
  • Capability inventory: The skill is restricted to read-only file access and does not have network or file-write capabilities.\n
  • Sanitization: There is no sanitization of the file content before the review is conducted.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 04:57 AM