promote-to-prod
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools including the GitHub CLI (
gh),yq, andgitto interact with repository state and trigger CI/CD workflows. These actions are aligned with the skill's stated purpose of managing deployments. - [EXTERNAL_DOWNLOADS]: The skill fetches configuration data (YAML) from the official
PostHog/chartsrepository on GitHub. This is a legitimate operation for resolving image references within the vendor's infrastructure. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by parsing external YAML data and interpolating values into shell commands. However, the risk is mitigated by the source being a controlled vendor repository and the requirement for a manual approval gate in the GitHub Actions environment before any promotion is finalized.
- Ingestion points:
state/duckgres.yamlviagh api. - Boundary markers: Absent.
- Capability inventory: Shell execution of
gh workflow run,gh api, andgit log. - Sanitization: None; values are interpolated directly into shell strings.
Audit Metadata