skills/danicat/skills/google-oss/Gen Agent Trust Hub

google-oss

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the official 'addlicense' tool from Google's GitHub repository using the command go install github.com/google/addlicense@latest. This installation targets a well-known organization and is the standard method for obtaining this utility.
  • [COMMAND_EXECUTION]: The skill uses shell commands and a dedicated script (scripts/apply-license.sh) to execute the addlicense binary for applying and verifying license headers. These actions are aligned with the stated purpose of repository compliance and licensing management.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface by processing source code files within a target directory to apply license headers.
  • Ingestion points: Local repository source files identified via globs or directory paths in SKILL.md and scripts/apply-license.sh.
  • Boundary markers: None explicitly defined in the skill instructions for the tool's output.
  • Capability inventory: Includes file system modification (writing headers) and network operations (tool installation).
  • Sanitization: The skill delegates content modification to the addlicense utility, which is designed to append comment blocks and does not interpret file content as executable instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 02:38 AM