install-scripts

Warn

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell tools such as 'cp' and 'chmod' to deploy scripts into the '.claude/scripts/' directory. This establishes a persistence mechanism where executable code is placed in a hidden project folder and made runnable across sessions.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through user-provided arguments like '--skill ', which are used for file path construction without defined sanitization.
  • Ingestion points: User-supplied arguments such as --skill and script names in the installation workflow.
  • Boundary markers: No instructions or delimiters are present to protect the prompt from injection in the argument values.
  • Capability inventory: Full file system access through the Read and Write tools, alongside shell command execution (Bash).
  • Sanitization: There are no explicit validation or sanitization steps to ensure the provided names do not result in directory traversal or execution of unintended files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 20, 2026, 07:24 PM
Security Audit — agent-trust-hub — install-scripts