generate-demo-voicebot
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from external websites to create personalized voice bot prompts.
- Ingestion points: The
scrape_lead_website.pyscript ingests data from user-provided URLs into the agent context. - Boundary markers: The documentation does not specify the use of boundary markers or instructions to ignore embedded commands within the scraped content.
- Capability inventory: The skill executes local Python scripts, performs file operations in
.tmp/, and interacts with external APIs (VAPI, Vercel). - Sanitization: There is no evidence of sanitizing or validating the scraped content before it is interpolated into the voice assistant's system prompt.
Audit Metadata