stakeholder-management-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted text data from stakeholder comments which could be used to inject instructions into generated reports. \n
- Ingestion points: The 'comments' array in the input JSON (referenced in consultation_input_schema.json). \n
- Boundary markers: No boundary markers or 'ignore embedded instructions' warnings were found in the processing logic. \n
- Capability inventory: The skill main script (consultation_summarizer.py) performs local file read and write operations for report generation. \n
- Sanitization: The validators.py module checks data types and string lengths but does not perform content sanitization for LLM injection patterns. \n- [External Downloads] (SAFE): No patterns of remote script execution or external package installations from untrusted sources were detected in the provided source code.
Audit Metadata