skills/diskd-ai/ccbox/ccbox-insights/Gen Agent Trust Hub

ccbox-insights

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Data Exposure] (LOW): The skill accesses session logs via the ccbox CLI. These logs are a source of sensitive information as they may contain environment variables, API call details, and proprietary code from previous agent interactions. Accessing this data is inherent to the skill's primary purpose.
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted historical log data which could contain malicious instructions embedded by an attacker in a previous session. * Ingestion points: ccbox history and ccbox sessions (SKILL.md). * Boundary markers: None identified in the workflow to separate log data from agent instructions. * Capability inventory: Shell execution (ccbox) and file system access. * Sanitization: No sanitization of log content is performed before processing.
  • [Command Execution] (SAFE): The skill requires and uses the ccbox CLI tool. The commands used (projects, sessions, history) are consistent with the skill's stated goal of log analysis and do not exhibit malicious behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 03:24 PM