skill-generator

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts such as bash scripts/generate-skill.sh and bun scripts/validate-skill.ts to perform its primary function of creating and verifying skill structures.
  • [DYNAMIC_EXECUTION]: The generator script dynamically creates new shell scripts and sets them as executable using chmod +x. This is standard behavior for a template generation tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it ingests a user-provided skill name and target directory. The skill name is sanitized using a strict regular expression (^[a-z0-9]+(-[a-z0-9]+)*$) in the shell script, which prevents command injection or directory traversal via the name parameter. The script uses standard file system capabilities (mkdir, cat, sed, chmod) for templating tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 08:14 AM