build-local
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands to build and serve applications based on scripts found in the project's own manifests and configuration files (SKILL.md).
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with project files and manifests within the local working tree, which represents an attack surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The agent reads project manifest files (e.g., package.json), lockfiles, and scripts from the local working tree (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are defined for the project files.
- Capability inventory: The skill possesses capabilities to run shell commands, manage background processes, and read local files (SKILL.md).
- Sanitization: There is no explicit requirement for the agent to sanitize or validate the scripts or commands extracted from the project configuration before execution.
Audit Metadata