vibe
Warn
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a dependency using
npx skills add heredotnow/skill, which downloads and runs code from an unverified external source.\n- [COMMAND_EXECUTION]: The skill executes a local shell script located at~/.agents/skills/here-now/scripts/publish.shto handle website deployment.\n- [INDIRECT_PROMPT_INJECTION]: The skill generates and reviews HTML and JavaScript code based on user-provided natural language descriptions, creating a surface for potential injection of malicious scripts into the generated website.\n - Ingestion points: Natural language descriptions for website generation in
SKILL.md.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined.\n
- Capability inventory: The skill writes to the local filesystem (
./vibe-output/) and executes deployment scripts (publish.sh).\n - Sanitization: No logic is provided to sanitize user-provided text or validate the generated code for security vulnerabilities like XSS.
Audit Metadata