repo-healthcheck-node
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard environment verification commands like node --version, pnpm install, and pnpm build. It can also execute custom installation and build commands extracted from repository documentation.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by parsing and following instructions from untrusted files such as AGENTS.md and CLAUDE.md. (1) Ingestion points: AGENTS.md, CLAUDE.md, package.json, .nvmrc, .node-version. (2) Boundary markers: Absent; commands are executed directly as parsed. (3) Capability inventory: Execution of shell commands via Bash. (4) Sanitization: Absent; the skill does not validate command strings before execution.
Audit Metadata