landing-from-brief

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests user-provided briefs to generate landing page code and content, creating a surface for indirect prompt injection attacks where malicious instructions in the brief could influence the generated output or deployment process.\n
  • Ingestion points: User-supplied landing page briefs (SKILL.md).\n
  • Boundary markers: None; the instructions do not specify the use of delimiters or 'ignore' warnings to isolate the untrusted brief content.\n
  • Capability inventory: The skill is authorized to write files to the project directory and perform network operations via API endpoints (e.g., POST /api/projects, POST /api/projects/:uuid/deploy).\n
  • Sanitization: There are no explicit instructions for validating or sanitizing the brief's content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 06:56 AM
Security Audit — agent-trust-hub — landing-from-brief