db-reset
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it instructs the agent to identify and execute commands derived from 'project tooling'.
- Ingestion points: Local project configuration files and tooling output.
- Boundary markers: None mentioned in the workflow to separate data from instructions.
- Capability inventory: Execution of destructive shell commands (reset/seed).
- Sanitization: No validation or sanitization of identified command patterns is described.
- [No Code] (SAFE): No scripts, binaries, or executable logic files were found in the skill.
Audit Metadata