deploy-safety
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documents standard development and deployment practices, including branch management, testing, and the use of the Vercel CLI for environment management.
- [PROMPT_INJECTION]: The skill identifies external data sources for post-deployment verification that could serve as surfaces for indirect prompt injection.
- Ingestion points: In
SKILL.md, the agent is instructed to verify deployments by checking browser consoles, server logs, and error tracking platforms like Sentry. These external sources can be populated with untrusted data by end-users or attackers. - Boundary markers: Absent. The skill does not provide delimiters or instructions to treat data from these logs as untrusted or to ignore embedded instructions.
- Capability inventory:
SKILL.mdenables capabilities for file system operations (git), package management (npm), deployment management (vercel), and network requests (curl). - Sanitization: Absent. There are no instructions for the agent to sanitize or filter the content retrieved from logs before processing it.
Audit Metadata