cli-anything-hub

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a live catalog of available tools from https://clianything.cc/SKILL.txt to provide the agent with a searchable directory of software.
  • [COMMAND_EXECUTION]: The skill instructs the agent to install and run software using pip and dynamically generated command names (e.g., cli-anything-kdenlive), which involves executing code on the host system.
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by ingesting a remote text file (SKILL.txt) that contains instructions and commands for the agent to follow.
  • Ingestion points: The catalog at https://clianything.cc/SKILL.txt is read and processed by the agent.
  • Boundary markers: None. The content is presented as authoritative guidance for tool discovery and installation.
  • Capability inventory: The skill has the capability to perform package installations (pip install) and execute shell commands.
  • Sanitization: There is no evidence of sanitization or verification of the remote catalog's content before the agent acts upon the instructions within it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:02 AM
Security Audit — agent-trust-hub — cli-anything-hub