gplay-iap-setup

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection (Category 8) by instructing the agent to execute shell commands (gplay) that accept untrusted parameters such as package names, SKUs, and JSON configuration data.
  • Ingestion points: Command arguments --package, --sku, and --json in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Execution of the gplay CLI tool for monetization management.
  • Sanitization: No input validation or escaping procedures are provided in the skill instructions.
  • [COMMAND_EXECUTION]: The skill documentation includes examples of dynamic execution (Category 10) where configuration files (e.g., product.json, subscription.json) are generated and subsequently passed to the gplay CLI tool for execution. This is categorized as low-risk behavior as it follows standard configuration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:29 PM