office-scan-config
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a JSON schema hosted on the author's GitHub repository (
Community-Access/accessibility-agents). This is a legitimate vendor resource used for configuration validation. - [INDIRECT_PROMPT_INJECTION]: The skill manages and validates
.a11y-office-config.jsonfiles which are consumed by external tools. - Ingestion points: Reads existing configuration files from the project environment for editing and validation.
- Boundary markers: Uses a structured JSON format and specifically mentions checking the
versionfield. - Capability inventory: The skill is designed to create, read, and write configuration files on the local filesystem.
- Sanitization: The instructions explicitly require the agent to verify that rule IDs match the internal reference tables and that severity filters use valid values ("error", "warning", "tip").
Audit Metadata