skills/erphq/skills/deploy-static/Gen Agent Trust Hub

deploy-static

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructions specify reading authentication credentials from ~/.build-host/credentials.json. This is a sensitive file path, but in this context, it is a vendor-defined resource used for its intended purpose of authenticating with the build.host API.
  • [PROMPT_INJECTION]: The skill processes user-provided project files and directories for deployment, creating an attack surface for indirect prompt injection.
  • Ingestion points: Project directory or git repository content (SKILL.md).
  • Boundary markers: None present in the instructions.
  • Capability inventory: File system read access and network POST requests to the build.host API for deployment (SKILL.md).
  • Sanitization: No sanitization or verification of user-provided file content is specified before deployment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 04:43 PM
Security Audit — agent-trust-hub — deploy-static