social-content
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external social media content to reverse-engineer performance patterns, creating a surface for indirect prompt injection.
- Ingestion points: The 'Reverse Engineering Viral Content' framework in
references/detailed-guide.md(Step 2: SCRAPE) directs the agent to collect 500-1000+ posts from external creators on platforms like LinkedIn and Twitter/X using third-party scrapers or manual research. - Boundary markers: The instructions lack specific boundary markers or 'ignore' directives to prevent the agent from obeying malicious instructions that might be embedded in the scraped social media text.
- Capability inventory: The skill claims the agent has 'direct access to a scheduling platform that publishes to all major social networks', which means a successful injection could lead to unauthorized or malicious social media posts being scheduled.
- Sanitization: There are no requirements for sanitizing, filtering, or validating the external content before the agent processes it for analysis and template generation.
Audit Metadata