contact-research
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- External Data Processing: The skill is designed to ingest and display information from the Common Room platform, including professional backgrounds, activity signals, and community engagement. This is the primary intended function of the skill.
- Ingestion Points: Data enters the agent context through the Common Room API based on user-provided identifiers like names, emails, or social media handles.
- Boundary Markers: The skill utilizes structured Markdown headers to organize findings, though it does not explicitly define unique delimiters for isolating external user-generated content (such as community posts) from the agent's internal instructions.
- Capability Inventory: The skill's operations are limited to data retrieval and presentation. There are no scripts or instructions present that perform file system modifications, network exfiltration, or command execution.
- Sanitization: The instructions focus on data quality and the avoidance of speculation, which promotes reliable output.
- Data Integrity Standards: The skill includes explicit instructions to avoid fabricating profile data when matches are not found. This 'no-speculation' policy is a positive reliability practice that reduces the risk of generating inaccurate information.
Audit Metadata