Skills
Navigate
skills/alisonaquinas/llm-shared-skills/tree/Gen Agent Trust Hub

tree

Fail

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The installation scripts scripts/install.sh and scripts/install.ps1 execute system-level package management commands including apt-get, brew, dnf, pacman, and apk to install software dependencies.
  • [COMMAND_EXECUTION]: The PowerShell script scripts/install.ps1 explicitly uses sudo to execute commands with administrative privileges on Linux systems.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes directory structures and file names which are untrusted data.
  • Ingestion points: Directory listing output from tree, find, or ls commands.
  • Boundary markers: No delimiters or instructions are used to separate the directory data from the agent's instructions.
  • Capability inventory: The skill has the ability to execute shell commands and modify the system state through installation scripts.
  • Sanitization: No sanitization or validation of file/directory names is performed before the agent processes them.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 8, 2026, 04:17 PM
Security Audit — agent-trust-hub — tree