NYC
skills/johnlindquist/claude/cass/Gen Agent Trust Hub

cass

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill recommends installing the 'cass' binary via 'cargo install'. This is an unverified dependency from a source not listed in the trusted organizations.
  • COMMAND_EXECUTION (LOW): The core functionality of the skill is built around executing external 'cass' commands. While expected for a CLI-based skill, it involves running unverified local code.
  • PROMPT_INJECTION (LOW): The skill presents an indirect prompt injection surface. Ingestion points: Processes session history files from multiple AI agents (Claude, Cursor, Aider, etc.). Boundary markers: None specified in the CLI search output or view commands to delimit untrusted historical content. Capability inventory: The agent possesses shell execution and file system access permissions. Sanitization: No evidence of sanitization or filtering of historical content before it is presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM