linux-clipboard

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a vulnerability surface for indirect prompt injection.
  • Ingestion points: The agent reads external data from the system clipboard using 'xclip -selection clipboard -o' and 'xsel --clipboard --output' (SKILL.md).
  • Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore or isolate potentially malicious instructions embedded in the clipboard content.
  • Capability inventory: The skill executes shell commands (xclip, xsel) and includes examples for reading local file content via stdin redirection (SKILL.md).
  • Sanitization: Absent. There is no evidence of filtering, escaping, or sanitizing the data ingested from the clipboard.
  • [COMMAND_EXECUTION]: The skill relies on system-level command execution to interact with the clipboard and includes installation instructions that use 'sudo' with package managers (apt, dnf), which requires elevated permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM