ads-creative

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide the agent with a checklist and scoring framework for ad creative audits. It uses local reference files for configuration and benchmarks, which is a standard and safe practice for this type of task.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from local reference files (ads/references/platform-specs.md, ads/references/benchmarks.md, ads/references/scoring-system.md).
  • Ingestion points: Reads local markdown files for specs and benchmarks.
  • Boundary markers: Absent.
  • Capability inventory: Limited to reading local reference files and writing a report file (CREATIVE-AUDIT-REPORT.md). No network or system-level capabilities detected.
  • Sanitization: No explicit sanitization or instruction to ignore embedded directives in the read files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:41 PM
Security Audit — agent-trust-hub — ads-creative