laundry-planner
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: A comprehensive review of the skill's instructions and reference files found no evidence of prompt injection, malicious command execution, or data exfiltration. The skill follows best practices for security by advising against hardcoding sensitive identifiers or credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill contains logic to ingest and update data from an external Notion database. This vulnerability surface is managed by clear instructions for the agent to verify data status and handle information conservatively.
- Ingestion points: The Notion database "Wäsche-Inventar" accessed via a Notion connector.
- Boundary markers: The instructions mandate checking the 'Datenstatus' (data status) field to distinguish between verified data and assumptions.
- Capability inventory: The skill can read/write to the Notion workspace and update local markdown files; it does not possess broader network or system capabilities.
- Sanitization: Instructions explicitly warn against including private credentials or identifiers in the skill's public repository.
Audit Metadata