Skills
Navigate
skills/hachej/boring-stack/boring-new-app/Gen Agent Trust Hub

boring-new-app

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gh CLI to perform administrative actions on GitHub, including repository creation, secret configuration, and permission management.\n- [EXTERNAL_DOWNLOADS]: Fetches an initialization tool directly from the author's GitHub repository (hachej/boring-factory) using the npx github: syntax.\n- [REMOTE_CODE_EXECUTION]: Executes remote code from the vendor's GitHub repository to bootstrap new application repositories.\n- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied strings which are used as arguments in shell commands, creating a potential surface for injection.\n
  • Ingestion points: Variables such as OWNER/NAME, EXPERT, BOT, and TITLE are collected from the user (documented in SKILL.md).\n
  • Boundary markers: No explicit delimiters or warnings are used in SKILL.md to isolate user-provided strings within the generated shell commands.\n
  • Capability inventory: The skill uses npx and gh in SKILL.md to execute commands that interact with the local filesystem and remote GitHub APIs.\n
  • Sanitization: SKILL.md does not specify sanitization or escaping of user-provided inputs before interpolation into npx command strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 02:08 PM