skills/baarai/artex/scopesentry/Gen Agent Trust Hub

scopesentry

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external security scans, which serves as an ingestion point for untrusted content.
  • Ingestion points: The skill utilizes tools like list_assets, get_asset_detail, list_tasks, and list_projects to retrieve data (such as web page titles, service banners, and vulnerability descriptions) from scanned external targets.
  • Boundary markers: No explicit instructions or delimiters are provided in the skill to warn the agent about potentially malicious instructions embedded in scan results.
  • Capability inventory: The skill has the ability to create new projects (create_project), initiate scan tasks (create_scan_task), and modify asset metadata (add_asset_tag), which could be targeted by a successful injection.
  • Sanitization: The instructions do not define any validation or sanitization requirements for the content retrieved from the ScopeSentry API.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 03:10 AM