skills/cryskai/crysk/crysk-ci-setup/Gen Agent Trust Hub

crysk-ci-setup

Warn

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONPERSISTENCEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill frequently uses npx -y crysk <command>, which downloads and executes the crysk package from the NPM registry at runtime. This provides a vector for executing code from an external source during the setup process.
  • [DATA_EXFILTRATION]: Instructions in references/opencode-ci.md prompt the agent to read the local auth.json file at ~/.local/share/opencode/auth.json using a Python script. This file contains sensitive authentication tokens and provider configurations.
  • [PRIVILEGE_ESCALATION]: The skill performs high-privilege operations such as setting GitHub repository secrets (gh secret set) and modifying branch protection rules via the GitHub API (gh api -X PUT ... branches/<default>/protection).
  • [PERSISTENCE]: The skill scaffolds a persistent GitHub Actions workflow (.github/workflows/crysk.yml) that executes on repository events like pull requests and comments, ensuring code execution in the CI environment.
  • [INDIRECT_PROMPT_INJECTION]: The CI workflow reacts to pull request comments (e.g., /crysk review).
  • Ingestion points: Pull request comments (issue_comment event) and pull request diffs.
  • Boundary markers: The skill relies on GitHub's write-access checks for comment authors but lacks explicit delimiters to prevent malicious instructions within the PR content from influencing the agent's behavior.
  • Capability inventory: Access to GitHub tokens, repository secrets, and status check manipulation.
  • Sanitization: Permission verification for command triggers is implemented, but content-level sanitization for ingested data is not specified.
  • [DYNAMIC_EXECUTION]: The skill uses a Python script passed via a shell heredoc (`python3
  • <<'PY') to dynamically parse local credential files. It also utilizes npx` for dynamic execution of the CLI tool.
  • [COMMAND_EXECUTION]: Multiple shell commands are executed using git, gh, and python to inspect repository state and apply configurations.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and references external code including the crysk NPM package and GitHub Actions like cryskai/crysk@v0 and actions/checkout@v4.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 29, 2026, 08:00 AM