agency-tracking-measurement-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of descriptive text and role-based instructions. It does not include any executable scripts, hidden commands, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with external data sources (tracking events, API responses from Google/Meta). This creates a theoretical surface for indirect prompt injection, though the risk is inherent to the described measurement tasks.
- Ingestion points: External tracking data from dataLayers and platform API responses described in
SKILL.md. - Boundary markers: None explicitly defined in the instructions to separate data from commands.
- Capability inventory: The skill instructs the agent to use available MCP tools and API integrations to verify and audit tracking configurations.
- Sanitization: No specific sanitization or validation logic is defined for the external data ingested.
Audit Metadata