privacy-jp

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of generating source code from user-provided data.
  • Ingestion points: User input is collected during a multi-step interview process defined in the skill's workflow.
  • Boundary markers: The skill does not implement delimiters or 'ignore embedded instructions' warnings for the data being ingested.
  • Capability inventory: The skill writes multiple TSX and MDX files to the project directory, which could lead to code injection if user input contains malicious instructions.
  • Sanitization: No sanitization or escaping mechanisms are specified for the user input before it is written to the files.
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to an external Discord server (https://discord.gg/wQWpEpnBfE) for community support and updates, which is a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 04:53 AM
Security Audit — agent-trust-hub — privacy-jp