kernel-dev-build
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior or security risks were identified. The skill follows best practices for repository maintenance and diagnostic workflows.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads external project files such as package.json and CI configurations to execute build commands, which creates a potential surface for indirect prompt injection if those files are compromised.\n
- Ingestion points: The skill inspects repository scripts, CI entrypoints, and documentation to determine execution steps.\n
- Boundary markers: There are no explicit instructions in the skill to delimit or ignore embedded instructions in the processed data files.\n
- Capability inventory: The skill leverages shell command execution for build, type-check, test, and lint operations.\n
- Sanitization: The skill does not explicitly require validation or sanitization of scripts extracted from project files before they are executed.
Audit Metadata