deploy-staging
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill executes local shell scripts
./scripts/deploy-staging.shand./scripts/rollback-staging.sh. While consistent with the skill's purpose for deployment, this allows for the execution of any commands contained within those files with the agent's current privileges. This represents a risk if the repository content is not fully trusted. - [EXTERNAL_DOWNLOADS] (LOW): The skill uses
curlto perform a health check onhttps://staging.example.com/health. This is a network operation to a non-whitelisted domain, though it is used here as a placeholder for a status check. - [PROMPT_INJECTION] (SAFE): No instructions designed to override the agent's system prompt or bypass safety guardrails were detected.
- [DATA_EXFILTRATION] (SAFE): No attempts to access sensitive files (like SSH keys or credentials) or exfiltrate private data were found.
Audit Metadata