ads-creative
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and configuration files were analyzed for malicious patterns, and no instances of obfuscation, hardcoded credentials, or unauthorized system access were found.\n- [NO_CODE]: This skill consists entirely of instructional Markdown content and YAML configuration. It does not include or execute any scripts, binaries, or automated tasks.\n- [PROMPT_INJECTION]: The skill processes external content (creative assets and performance data), which represents a surface for indirect prompt injection.\n
- Ingestion points: Creative assets and performance data collected from active advertising platforms as described in SKILL.md.\n
- Boundary markers: None identified in the provided files.\n
- Capability inventory: The skill is limited to reading local reference files (platform specs, benchmarks) and generating audit reports.\n
- Sanitization: No explicit sanitization or input validation logic is defined.
Audit Metadata