playbook-reputation-management
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of text-based guidelines and templates for social media consulting. It contains no executable code, remote script downloads, or dangerous shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided business data and reputation metrics. 1. Ingestion points: The 'Required Input' section in SKILL.md. 2. Boundary markers: None identified to delimit external input. 3. Capability inventory: No high-privilege tools or dangerous scripts are included. 4. Sanitization: No explicit sanitization of user-provided business names or reputation data is defined.
- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. The skill refers to reputable news outlets and business directories consistent with its stated geographic focus in East Africa.
Audit Metadata