skills/tonone-ai/tonone/touch-release/Gen Agent Trust Hub

touch-release

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill performs environment detection by scanning for files like Matchfile, .mobileprovision, and .gradle to identify the project's code signing configuration. This is a legitimate requirement for automating mobile release pipelines.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external project files such as package.json, pubspec.yaml, and Fastfile using shell commands.
  • Ingestion points: Files are read via cat and grep in SKILL.md (Step 0).
  • Boundary markers: None used during file reading.
  • Capability inventory: The skill uses Bash, Write, Edit, and WebFetch tools.
  • Sanitization: No explicit sanitization of read data is performed, though the data is primarily used for identifying project type and state.
  • [SAFE]: The skill includes explicit security best practices, such as recommending that users do not commit match passphrases or Android keystore passwords to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 02:48 PM
Security Audit — agent-trust-hub — touch-release