skills/klotzkette/claude-fuer-deutsches-recht/kanzlei-cowork-kaltstart-interview/Gen Agent Trust Hub
kanzlei-cowork-kaltstart-interview
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from existing configuration files and mandate records which could potentially contain malicious instructions.
- Ingestion points: The skill reads from ~/.claude/plugins/config/claude-fuer-deutsches-recht/kanzlei-allgemein/CLAUDE.md and files within the mandate subdirectories.
- Boundary markers: There are no explicit instructions to the agent to treat data read from these files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses the capability to read from and write to the local file system within the specified plugin paths.
- Sanitization: The instructions do not include steps to sanitize or validate the content retrieved from the file system before processing.
Audit Metadata