skills/umputun/cc-thingz/md-copy/Gen Agent Trust Hub

md-copy

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to manage temporary files and interact with system clipboard utilities such as pbcopy, xclip, and xsel.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content generated during the AI session without sanitization.\n
  • Ingestion points: The skill ingests the final answer or response from the current session (SKILL.md).\n
  • Boundary markers: The workflow uses a quoted heredoc ('EOF') to ensure session content is written to a temporary file without triggering shell variable expansion or command substitution.\n
  • Capability inventory: The skill has the capability to write files to the /tmp/ directory and modify the system clipboard via subprocess calls.\n
  • Sanitization: No validation or sanitization is performed on the session content before it is placed on the clipboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:46 PM
Security Audit — agent-trust-hub — md-copy