skills/ry-run/run-skills/vercel-skill/Gen Agent Trust Hub

vercel-skill

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted external data which could contain malicious instructions aimed at overriding agent behavior.
  • Ingestion points: Tools such as web_fetch_vercel_url, get_runtime_logs, get_deployment_build_logs, and search_vercel_documentation (SKILL.md) ingest content from external URLs, build/runtime logs, and search results into the agent context.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore or isolate potential commands within the ingested data.
  • Capability inventory: The skill provides access to potentially sensitive operations including deploy_to_vercel, reply_to_toolbar_thread, and change_toolbar_thread_resolve_status (references/vercel-skill.md), which could be triggered by malicious content in the ingestion points.
  • Sanitization: No sanitization or validation of the fetched external content is specified before the data is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 07:20 AM
Security Audit — agent-trust-hub — vercel-skill