ads-manager-agent
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'openclaw-adspirer' Node.js plugin to access the ad management tools. This is a vendor-owned resource provided by the author openclaw.\n- [COMMAND_EXECUTION]: Uses CLI commands for setup and account management, including 'openclaw plugins install' and 'openclaw adspirer login'.\n- [DATA_EXFILTRATION]: Communicates with mcp.adspirer.com and www.adspirer.com to manage ad platform integrations and handle API requests. These are the primary service endpoints for the skill.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it analyzes data from external sources.\n
- Ingestion points: Ad platform performance data (search terms), user-provided URLs for website analysis, and metadata from externally hosted creative assets.\n
- Boundary markers: Explicit delimiters for separating untrusted external content from system instructions are not specified in the current configuration.\n
- Capability inventory: The skill can execute API calls to create, update, and manage campaigns and budgets across four major ad platforms.\n
- Sanitization: Risks are mitigated by safety protocols requiring explicit user confirmation for all write operations and ensuring all new campaigns are created in a 'PAUSED' status for manual review.
Audit Metadata