social-content
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: A detailed inspection of the skill instructions and metadata found no evidence of malicious patterns, hardcoded credentials, or exfiltration attempts.
- [NO_CODE]: The skill consists exclusively of markdown documentation and content templates; no Python, Node.js, or shell scripts are present.
- [PROMPT_INJECTION]: The 'Reverse Engineering Viral Content' section suggests a workflow for scraping and analyzing a large volume of external social media posts. This creates a surface for indirect prompt injection, where an agent could potentially execute instructions hidden within the data it is instructed to analyze.
- Ingestion points: Social media content scraped from external platforms like LinkedIn or X as part of the 'Reverse Engineering' workflow.
- Boundary markers: Absent. The documentation does not provide specific instructions to use delimiters or ignore embedded commands in the analyzed data.
- Capability inventory: None. The skill does not provide its own tools, though the description mentions access to a scheduling platform.
- Sanitization: Absent. The workflow does not describe methods for filtering or sanitizing the ingested social media content.
Audit Metadata