kontaktbuch
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation providing guidelines for an AI agent to handle contact information privacy-consciously. No code (Python, Node.js), shell scripts, or external dependencies are included.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process untrusted external data (contact lists provided by the user), it poses no risk as it does not define or utilize any tools or executable functions that could be exploited by embedded instructions.
- Ingestion points: User-supplied contact data (mentioned in the workflow in
SKILL.md). - Boundary markers: Explicit instructions in the workflow mandate using 'only information supplied in the current request' and 'labeling assumptions'.
- Capability inventory: No tools, subprocess calls, or network operations are present in the skill files.
- Sanitization: Not applicable as no automated tool execution occurs.
Audit Metadata