deploy
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute deployment commands, including Makefile targets, terraform apply, fly deploy, and Vercel CLI commands. This is required for its primary function but grants the agent shell access to the environment.
- [CREDENTIALS_UNSAFE]: The instructions direct the agent to identify changes in environment variables and secrets during the risk assessment phase. While necessary for deployment auditing, this involves the handling of sensitive configuration data.
- [PROMPT_INJECTION]: The skill processes untrusted data from the repository which presents a surface for indirect prompt injection.
- Ingestion points: git log output, git diff output, Makefile content, infrastructure configuration files, and database migration scripts.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The agent has the capability to execute shell commands via make, terraform, and other deployment tools.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content of commit messages or configuration files before processing.
Audit Metadata