weekly-outreach-report
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No evidence of malicious behavior, data exfiltration, or unauthorized command execution was found. The skill operates within its stated purpose of report generation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as LinkedIn automation tools, email platforms, and client exports (CSV/Sheets).
- Ingestion points: Data is pulled from external platforms and user-provided files in Step 1 and Step 2.8.
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the external content.
- Capability inventory: The skill instructs the agent to create reporting pages and pull live data, involving basic data retrieval and formatting capabilities.
- Sanitization: No specific content sanitization or validation logic is outlined in the instructions for processing prospect replies.
Audit Metadata