log-leave
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by incorporating untrusted user input into a local YAML configuration file.
- Ingestion points: User-provided employee names, roles, and notes are collected during the interaction (defined in SKILL.md).
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands when writing the user data to the file system.
- Capability inventory: The skill performs file system read and write operations within the plugin's configuration directory (~/.claude/plugins/config/).
- Sanitization: The instructions do not provide mechanisms for validating, escaping, or filtering user input before it is written to the structured YAML file.
Audit Metadata