ads-audit
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from advertising account exports and APIs, creating a vulnerability surface for indirect prompt injection.\n
- Ingestion points: SKILL.md identifies advertising exports, screenshots, and API responses as primary data inputs.\n
- Boundary markers: There are no specified boundary markers or instructions to ignore embedded commands within the processed data.\n
- Capability inventory: The skill has file-writing capabilities (e.g., ADS-AUDIT-REPORT.md) and delegates tasks to subagents.\n
- Sanitization: The documentation does not describe any sanitization or validation routines for the ingested content.\n- [EXTERNAL_DOWNLOADS]: The skill references external tools and third-party Model Context Protocol (MCP) servers for automated data gathering.\n
- Evidence: References cohnen/mcp-google-ads and AdsMCP/tiktok-ads-mcp for fetching advertising account data.\n- [COMMAND_EXECUTION]: The skill is designed to execute local utility scripts to retrieve data from platform APIs.\n
- Evidence: Mentions the execution of scripts/api/meta_fetch.py, scripts/api/google_fetch.py, and scripts/api/tiktok_fetch.py.
Audit Metadata