youtube-viral-optimizer
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated ingestion of external data to generate content.\n
- Ingestion points: The skill ingests data from external URLs and video transcripts via the InfraNodus:analyze_text and InfraNodus:analyze_google_search_results tools as part of its SEO-to-script workflow.\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat ingested data as untrusted or to ignore any embedded instructions.\n
- Capability inventory: The skill calls external analysis tools and generates structured video scripts, hooks, and titles where external content (like search intent or gap analysis) directly informs the agent's output.\n
- Sanitization: The instructions do not specify any validation or sanitization procedures for the data received from external sources before it is interpolated into script templates.\n- [DATA_EXFILTRATION]: The skill transmits video transcripts, topic keywords, and external URLs to the InfraNodus platform's MCP tools to perform knowledge mapping and SEO analysis. These tools are provided by the skill's author ('infranodus') and represent the core intended functionality for research and optimization.
Audit Metadata