background

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to how it handles external data.
  • Ingestion points: Untrusted user input is received through the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: There are no delimiters or 'ignore embedded instructions' warnings surrounding the interpolated input.
  • Capability inventory: The skill explicitly utilizes the Bash tool and Task tool for command and task execution, which are high-privilege operations.
  • Sanitization: No escaping, validation, or filtering of the $ARGUMENTS content is implemented before it is passed to the execution tools.
  • [COMMAND_EXECUTION]: The skill enables arbitrary command execution by instructing the agent to pass user-provided strings directly to shell-based tools (Bash tool with run_in_background=true). This pattern allows untrusted input to influence system-level operations without sufficient oversight or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:17 AM
Security Audit — agent-trust-hub — background