video-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill is purely instructional.\n- [INDIRECT_PROMPT_INJECTION]: The skill attempts to read project context from .claude/project-context.md or .cursor/project-context.md. While this constitutes a data ingestion surface, the skill lacks any executable code or sensitive tool access that could be exploited via indirect injection.\n
- Ingestion points: .claude/project-context.md, .cursor/project-context.md in SKILL.md\n
- Boundary markers: Absent\n
- Capability inventory: None detected (no scripts or tools requested)\n
- Sanitization: Absent
Audit Metadata