redundancy-pruner
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to bypass safety guidelines or override agent behavior. The instructions are strictly limited to text editing and formatting.
- [Data Exposure & Exfiltration] (SAFE): The skill reads from and writes to specific local markdown and configuration files within the user's workspace. It explicitly states 'Network: none' and contains no commands for external data transmission.
- [Remote Code Execution] (SAFE): There are no scripts, package dependencies, or commands that download or execute code from remote sources.
- [Persistence & Privilege Escalation] (SAFE): The skill does not attempt to modify system configuration files, shell profiles, or acquire elevated permissions.
- [Indirect Prompt Injection] (SAFE): While the skill processes user-provided markdown content, it lacks high-risk capabilities such as command execution or network access, and its scope is restricted to in-place text pruning.
Audit Metadata