bing-ai-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest and analyzes user-provided CSV and JSON exports from Bing Webmaster Tools, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: User-supplied Bing AI Performance CSV and JSON exports.
- Boundary markers: The SKILL.md file contains specific safety rules directing the agent to treat all user-supplied exports and config files as untrusted data and never as instructions.
- Capability inventory: Analysis of the skill files revealed no capabilities for shell command execution, network requests, or sensitive file writing.
- Sanitization: Instructions provided to the agent emphasize the use of aggregate evidence rather than raw sensitive data in reports.
Audit Metadata