playbook-audacious-content
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, focusing on marketing frameworks such as Schaefer's Audacity Index and Berger's STEPPS. It does not contain any code snippets, shell commands, or platform-specific tool calls.
- [SAFE]: No external data exfiltration or network patterns (e.g., curl, wget) are present. The skill only requests textual inputs (business name, location, recent posts) to generate a strategy.
- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the instructions or metadata.
- [SAFE]: While the skill ingests untrusted data (user-provided social media posts), it lacks any executable capabilities (no file-write, no subprocess execution), rendering the risk of indirect prompt injection effectively null in this context.
Audit Metadata