skills/cjakma/k-skill/hipass-receipt/Gen Agent Trust Hub

hipass-receipt

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several hipass-receipt commands to launch specialized Chrome instances, list usage history, and navigate to receipt popups.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the hipass-receipt npm package (a vendor resource) and playwright-core to enable browser automation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data from the Hi-pass website.
  • Ingestion points: The skill reads usage history and receipt details from https://www.hipass.co.kr via the list and receipt subcommands (SKILL.md).
  • Boundary markers: There are no specific instructions or delimiters defined to separate the scraped website content from the agent's instructions.
  • Capability inventory: The skill can execute local shell commands (the hipass-receipt CLI) and manipulate an active browser session via CDP.
  • Sanitization: No explicit sanitization or validation of the data retrieved from the website is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:48 AM
Security Audit — agent-trust-hub — hipass-receipt