The Agent Skills Directory

[SAFE]: The skill contains only natural language instructions and structured workflow guidelines for performing legal compliance documentation. No malicious patterns, base64 obfuscation, or persistence mechanisms were detected.
[NO_CODE]: There are no scripts, binaries, or executable code blocks associated with this skill. It relies entirely on the agent's reasoning capabilities within the provided legal framework.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external evidence such as contracts, protocols, and legal notices. This introduces a potential surface for indirect prompt injection where instructions could be hidden within the processed documents.
Ingestion points: Processes user-provided documents including 'Verwaltungsakte' (administrative acts), 'Vertragsurkunden' (contracts), and 'Schriftsätze' (pleadings).
Boundary markers: No specific delimiters or warnings to ignore embedded instructions in the source documents are provided.
Capability inventory: The skill is limited to text analysis and documentation generation; it does not list any high-risk tool access such as shell execution or file-system writing.
Sanitization: No explicit sanitization of document content is performed prior to analysis.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to verify legal norms via established German legal portals such as gesetze-im-internet.de and dejure.org. These are reputable, well-known services for legal research and represent safe external references for the skill's intended purpose.

dma-compliance-dokumentation-und-akte