import-command

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected. The skill processes external file content from .cursor/commands/ which could contain malicious instructions designed to hijack the agent's behavior during the conversion process.
  • Ingestion points: .cursor/commands/<command-name>.md (File read operation).
  • Boundary markers: Absent. The skill does not provide instructions to the agent to treat the input files strictly as data or to ignore embedded instructions.
  • Capability inventory: The agent can create new files in .claude/skills/ and modify CLAUDE.md.
  • Sanitization: Absent. No validation or escaping of the input content is specified.
  • Mitigation: The skill includes a human-in-the-loop 'Present for Approval' step (Step 6) before any files are created, which mitigates the risk of automated exploitation.
  • [NO_CODE] (SAFE): No executable scripts, binaries, or shell commands are included in the skill. All operations are carried out via natural language instructions to the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 01:20 PM