mentionedon-discovery-evidence
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a functional guide for integrating with the MentionedOn MCP service. All referenced URLs point to the official domain of the service (mentioned-on.com), and no suspicious command execution or data exfiltration patterns were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data supplied by users, such as AI-discovery signals and scan evidence. This creates a surface for potential indirect prompt injection attacks where malicious content in the data could attempt to influence the agent. The skill includes instructions to maintain clear separation between source labels, dates, and inferences to help manage this risk.\n
- Ingestion points: User-provided AI-discovery signals and scan evidence as described in SKILL.md.\n
- Boundary markers: Absent.\n
- Capability inventory: Access to analyze_discovery_readiness, build_visibility_action_plan, and summarize_scan_evidence tools.\n
- Sanitization: Absent.
Audit Metadata