social-content
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides strategic guidelines and templates for social media content creation. No malicious scripts, exfiltration code, or unauthorized access attempts were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to scrape and analyze external social media content from platforms like LinkedIn and Twitter/X. This process exposes the agent to untrusted data where malicious instructions could be embedded.
- Ingestion points: Collection of post content and engagement metrics from external social media creators.
- Boundary markers: No delimiters or safety instructions are provided to the agent for handling the scraped text.
- Capability inventory: Strategy generation and content creation. The skill claims the agent has access to a scheduling platform for publishing.
- Sanitization: No data validation or cleaning steps are defined for the analyzed social media data.
Audit Metadata