angebotsschreiben-offer-letter
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided documents, which serves as a potential ingestion point for untrusted instructions. The logic handles sensitive HR contexts, making it a target for malicious content embedded in resumes or contracts.\n
- Ingestion points: The agent is explicitly instructed to read provided documents in the 'Einstieg' section of SKILL.md.\n
- Boundary markers: Absent. No specific delimiters or safety warnings for external content are defined in the prompt instructions.\n
- Capability inventory: The agent generates various outputs including emails, checklists, and risk assessments based on ingested data.\n
- Sanitization: Absent. There is no mention of filtering or validating input text.\n- [NO_CODE]: The skill consists only of natural language instructions and does not contain any executable scripts or configuration files, reducing the risk of direct command execution or remote code execution.
Audit Metadata