setup-landscape
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
npx skills@latestandpnpm dlx skills@latestto download and execute the latest version of theskillspackage from the NPM registry at runtime.\n- [COMMAND_EXECUTION]: The skill automates repository management via multiple shell commands includinggit clone,git pull,git push, andgh pr createto manage branches and pull requests.\n- [EXTERNAL_DOWNLOADS]: The skill fetches external code by cloning repositories from GitHub usinggh repo clone <owner/repo>based on user-provided arguments.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes untrusted code and project context from various member repositories to map connections and domain models.\n - Ingestion points: Member repository code and project context files, as specified in Step 2 of SKILL.md.\n
- Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the analyzed code.\n
- Capability inventory: The skill has the capability to write to the file system (Step 3 and 4), push to Git repositories, and create pull requests.\n
- Sanitization: Absent; there is no mention of filtering or escaping content read from external repositories before it is processed or used to generate new files.
Audit Metadata