pr-hero-ci-setup
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands such as
npx -y pr-hero,git, andghto configure the CI environment, set secrets, and verify the setup. - [EXTERNAL_DOWNLOADS]: Downloads the
pr-heropackage from the npm registry usingnpx. This is a vendor-owned resource controlled by the author (juanmaagd). - [REMOTE_CODE_EXECUTION]: The generated GitHub Actions workflow executes the
juanmaagd/pr-hero@v0remote action. This is a vendor-owned resource used for the skill's primary purpose. - [DYNAMIC_EXECUTION]: Uses
npxto dynamically download and execute thepr-heroCLI tool at runtime during setup and within the CI environment. - [INDIRECT_PROMPT_INJECTION]: The skill sets up a CI pipeline that processes untrusted data from Pull Requests. 1. Ingestion points: Pull Request content, including diffs and comments, is processed by the CI action (SKILL.md, assets/workflow.yml). 2. Boundary markers: None mentioned in the workflow; handled by the pr-hero action. 3. Capability inventory: The workflow is granted permissions to write comments, update issue threads, and set commit statuses and checks across all scripts (assets/workflow.yml). 4. Sanitization: Sanitization and escaping of external content are expected to be handled by the pr-hero action.
Audit Metadata