kuerzen
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text and possesses tools to modify the file system (Write, Edit). This creates a surface for indirect prompt injection where malicious instructions embedded in a user's document could potentially influence agent behavior during the editing process.
- Ingestion points: User-provided text for editing and files accessed via the
Readtool. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are mandated for the input content.
- Capability inventory: The skill uses
Read,Write,Edit,Grep,Glob, andAskUserQuestiontools. - Sanitization: No input sanitization or validation of the processed text is implemented.
- [EXTERNAL_DOWNLOADS]: The README provides installation commands that download the skill from the author's public GitHub repository (
iamursky/sokrati). This represents a standard deployment method for the vendor's resources.
Audit Metadata