entgelttransparenz
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as employment figures, salary structures, job descriptions, and previous disclosure requests to generate legal assessments and roadmaps.
- Ingestion points: Data enters the context through the 'Eingaben' section defined in SKILL.md, which includes employee counts, salary data, and recruitment practices.
- Boundary markers: The skill instructions do not utilize specific delimiters or provide explicit warnings to the agent to ignore instructions that might be embedded within the provided HR data.
- Capability inventory: The skill coordinates multiple sub-agents (researcher, drafter, reviewer) to write reports, roadmaps, and legal disclosure responses.
- Sanitization: There is no evidence of input validation or instruction-based sanitization to prevent the agent from following malicious commands hidden in the data inputs.
Audit Metadata