compliance-check
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official MCP tools (
mcp__devtools__*) to interact with the vendor's own infrastructure atmcp.facebook.com. This is expected behavior for a compliance tool developed by the vendor. - [SAFE]: References to external documentation and installation guides point to the official GitHub repository for Facebook (
github.com/facebook/agentic-tools), which is a trusted source. - [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized data exfiltration was found. The skill follows a transparent workflow for data collection and reporting.
- [SAFE]: While the skill ingests external data (compliance status and app settings), it does not have exploitable capabilities like arbitrary command execution or file system writes, mitigating risks related to indirect prompt injection.
Audit Metadata