speed-to-lead
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs local analysis of CSV data via a provided Python script (
call_log.py). The script uses only Python standard libraries and does not initiate network requests or unauthorized file system operations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external CSV call log and message exports, presenting a potential injection surface.
- Ingestion points: Data is read from user-supplied CSV files by
scripts/call_log.py. - Boundary markers: The skill includes strict privacy directives to keep all customer data within the workspace and out of shared reports or version control.
- Capability inventory: The skill produces static markdown reports and summaries; it lacks capabilities for network exfiltration or administrative command execution.
- Sanitization: The Python script utilizes standard
csvparsing and regular expressions to extract specific fields like timestamps and digits, which serves as a basic form of data validation.
Audit Metadata