safe-settings

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external YAML configuration files to manage organization-level GitHub settings, which introduces a potential attack surface for indirect prompt injection if the configuration repository is compromised.
  • Ingestion points: Configuration files located at .github/settings.yml, .github/suborgs/*.yml, and .github/repos/*.yml (as described in SKILL.md and references/schema.md).
  • Boundary markers: The skill relies on structured YAML schema for data parsing but does not include specific prompt-level delimiters or instructions to ignore embedded commands within the configuration values.
  • Capability inventory: The skill's synchronization workflow executes git clone, npm ci, and npm run full-sync in assets/full-sync.yml, and utilizes gh CLI commands for secret and variable management.
  • Sanitization: Input validation and sanitization are delegated to the underlying safe-settings Probot application logic; no additional sanitization is implemented within the skill's instructional protocol.
  • [REMOTE_CODE_EXECUTION]: The synchronization workflow is designed to download and execute code from a remote repository at runtime.
  • Evidence: The GitHub Actions workflow in assets/full-sync.yml clones the github-community-projects/safe-settings repository, installs its dependencies via npm ci, and executes the application logic using npm run full-sync.
  • [EXTERNAL_DOWNLOADS]: The skill fetches tool source code and uses external workflows from well-known repositories.
  • Evidence: assets/full-sync.yml fetches code from github.com/github-community-projects/safe-settings and utilizes official GitHub Actions such as actions/checkout and actions/setup-node, which are correctly pinned to specific commit hashes for security.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage repository state, credentials, and reconciliation processes.
  • Evidence: SKILL.md instructs the user to execute gh variable set and gh secret set to configure GitHub App credentials, while the synchronization workflow in assets/full-sync.yml executes shell-based installation and execution commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 07:12 AM