catalog-commerce
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill interacts with Meta Ads account data, including product catalogs and pixel link configurations. This access is limited to the scope of the Meta Ads MCP and is the primary intended function of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the Meta Ads API (catalog lists, product counts, and event IDs). While this represents an attack surface where malicious data in a catalog could attempt to influence the agent, the skill includes explicit instructions for the agent to confirm with the user before performing any write operations, which serves as a human-in-the-loop guardrail.
- [COMMAND_EXECUTION]: The skill requests write access to the Meta Ads MCP to create product sets. These operations are restricted to the Meta Ads platform and require user confirmation at each step as per the instructions.
Audit Metadata