create-hook

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate shell scripts in directory paths such as ~/.claude/hooks/ and ensure they have executable permissions via chmod +x. These scripts are intended to facilitate automated development workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and examples from trusted organizations and well-known services, including official Claude documentation (docs.claude.com), GitHub repositories from the anthropics organization, and established development utilities such as Prettier and jq.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it analyzes untrusted project configuration files to determine which hooks to suggest.
  • Ingestion points: Reads local project files including package.json, tsconfig.json, .prettierrc, and .eslintrc.* (SKILL.md).
  • Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore potential instructions embedded within the analyzed configuration files.
  • Capability inventory: The skill has the capability to generate shell scripts, modify settings.json, and register hooks for automatic execution (SKILL.md).
  • Sanitization: No specific sanitization or validation steps are defined for processing the content retrieved from project configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 03:50 AM