app-store-rejection

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the appstore-release CLI from the vendor's GitHub repository (github.com/beydemirfurkan/appstore-release.git) if not found locally.
  • [REMOTE_CODE_EXECUTION]: Executes the downloaded CLI tool via node using spawnSync as part of its primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions embedded in processed data.
  • Ingestion points: The agent is instructed to read and classify App Store rejection messages pasted by the user (SKILL.md, Step 2).
  • Boundary markers: The instructions lack specific delimiters or instructions to ignore potential commands within the user-provided text.
  • Capability inventory: Includes execution of CLI commands, modification of store metadata, and build resubmission.
  • Sanitization: No evidence of input sanitization or validation for the rejection messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 05:59 PM