social-media-manager
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected in the skill instructions or associated scripts. All content aligns with the stated purpose of providing social media strategy and management tools.
- [SAFE]: The Python scripts (
content_calendar_generator.py,growth_tracker.py,social_audit_scorer.py) only import standard library modules (json,argparse,datetime,pathlib). They do not perform network requests, execute remote code, or access sensitive system directories. - [SAFE]: The skill operates on local JSON data files provided by the user for auditing and tracking. While this represents a data ingestion surface, the scripts lack dangerous capabilities (such as
eval(),subprocess, or network exfiltration) that would make them vulnerable to exploitable indirect prompt injection. - [SAFE]: Metadata and instructions are transparent and consistent with legitimate marketing automation and reporting tasks. No persistence mechanisms or privilege escalation attempts were identified.
Audit Metadata