pixel-conversions
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and metadata do not contain any malicious patterns. The skill explicitly requires read-only access and instructs the agent to make no changes to the environment.
- [PROMPT_INJECTION]: The skill processes external data, creating a surface for potential indirect prompt injection.
- Ingestion points: The skill accepts user-provided conversion counts via the
[MY STORE'S COUNT]placeholder inSKILL.mdand retrieves data from the Meta Ads API via an MCP tool. - Boundary markers: No explicit delimiters or boundary markers are used for the external data inputs.
- Capability inventory: The skill is limited to read-only access to Meta Ads data; it lacks file-write, network exfiltration, or command execution capabilities.
- Sanitization: No specific sanitization or validation logic is defined for the store count input.
Audit Metadata