kartellrecht-tt-gvo-eu-316-2014
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of legal contracts and IP agreements.
- Ingestion points: The agent is instructed to read user-provided documents including contracts, IP attachments, and party/product descriptions as specified in the 'Direktstart' section of
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be maliciously embedded within the processed legal text.
- Capability inventory: The skill does not possess high-risk capabilities such as network access, file system write permissions, or the ability to execute system commands; its primary function is to generate a structured analysis matrix.
- Sanitization: The instructions do not include any validation, filtering, or sanitization steps for the input data.
Audit Metadata