ads-create

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates on local files within the agent's current directory (e.g., brand-profile.json and ADS-AUDIT-REPORT.md) to synthesize information for a campaign brief. This behavior aligns with the stated purpose of generating advertising strategies from existing project data.\n- [PROMPT_INJECTION]: The skill processes external data from local JSON and Markdown files, which represents a surface for indirect prompt injection if those files contain untrusted content.\n
  • Ingestion points: brand-profile.json and ADS-AUDIT-REPORT.md (or *-audit-results.md) are read during Step 1 and Step 2.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading these files.\n
  • Capability inventory: The skill can read local files, spawn sub-agents (creative-strategist and copy-writer), and write output to campaign-brief.md.\n
  • Sanitization: No explicit validation or sanitization of the input file content is defined in the process logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — ads-create