safe-file-deletion

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No security issues detected. The skill acts as a defensive mechanism to ensure user consent is obtained before destructive actions are taken.
  • [NO_CODE] (SAFE): The skill consists entirely of markdown instructions and usage examples. There are no scripts, binaries, or configuration files that could execute malicious commands.
  • [PROMPT_INJECTION] (SAFE): The instructions use imperative language ("MUST", "Never bypass") to enforce safety constraints and prevent the agent from circumventing user approval prompts during file operations.
  • [DATA_EXFILTRATION] (SAFE): No network operations, API calls, or access to sensitive credentials/paths are present in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM