fristenbuch-fuehren
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted documents such as contracts, administrative acts, court briefs, and protocols to extract legal deadlines.
- Ingestion points: The skill explicitly instructs the agent to gather and check documents like "Verwaltungsakte, Vertragsurkunden, Schriftsätze, Bescheide" (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the content of these documents or to instruct the agent to ignore any embedded directives within them.
- Capability inventory: The agent has the capability to read these files and write updated status and audit information to the filesystem (e.g.,
fristenbuch.yaml,fristen-uebersicht.md). - Sanitization: No sanitization or validation logic is specified for the data extracted from these external documents before it is processed or written to the configuration file.
Audit Metadata