workflow-environment-ready
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute various shell commands to verify the local environment. This includes runtime version checks (e.g.,
node -v,python --version), dependency installation (e.g.,npm ci,pnpm install --frozen-lockfile,pip install -r), and the execution of project-specific scripts found inpackage.json,Makefile, orjustfile. While these are standard development tasks, executing scripts defined in the workspace environment is a powerful capability. - [INDIRECT_PROMPT_INJECTION]: The skill uses content from external, potentially untrusted repository files to drive its execution logic, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads
package.json,Makefile,README,.env.example, and CI workflow files to detect requirements and verification commands. - Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore malicious content embedded within these files.
- Capability inventory: The skill has the capability to execute shell commands, perform network connectivity checks (health requests, DB pings), and write to files (installation commands).
- Sanitization: Absent. The instructions do not include steps to sanitize or validate the scripts or environment variable names extracted from the repository files before they are used in commands.
Audit Metadata