oneshot-build

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill incorporates the @oneshot-agent/sdk Node.js package. This is the official software development kit provided by the vendor (oneshot-agent) to facilitate website creation and management through their platform.
  • [PROMPT_INJECTION]: The agent.build functionality supports a source_url parameter designed to analyze third-party websites for design inspiration. This creates an indirect prompt injection surface. Ingestion points: External content is fetched and analyzed from URLs provided in the source_url field within SKILL.md. Boundary markers: There are no documented delimiters or specific instructions provided to the agent to ignore potentially malicious instructions embedded in the source website's content. Capability inventory: The skill allows the agent to generate and deploy code based on its analysis of the input. Sanitization: The documentation does not specify any content filtering or sanitization processes for the data retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:25 PM
Security Audit — agent-trust-hub — oneshot-build