timesheet-aktenzeitung-umgang-ki
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (legal files, receipts, and case evidence) to generate structured outputs like YAML and Parquet files, creating a surface for indirect prompt injection attacks.
- Ingestion points: External documents and evidence provided to the agent for triage and time tracking as described in the workflow.
- Boundary markers: The instructions do not define delimiters or specific safety warnings to ignore instructions embedded within the ingested files.
- Capability inventory: The skill creates and writes structured files (timesheet.yaml, timesheet.parquet) based on the processed external content.
- Sanitization: There is no specific requirement for the agent to sanitize or validate the data extracted from documents before generating reports.
Audit Metadata