linkedin-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for local processing of user-supplied data exports. It does not perform any network operations, ensuring that user data remains on the local machine.
- [SAFE]: All included scripts (
post_performance_analyzer.py,pattern_miner.py,experiment_planner.py) use only Python standard library modules and do not include any remote code execution, persistence, or privilege escalation patterns. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (LinkedIn CSV/JSON exports).
- Ingestion points: Data enters through the
--inputargument in the analysis scripts. - Boundary markers: The scripts use structured parsing (CSV/JSON) which inherently provides some level of data separation.
- Capability inventory: The scripts are limited to mathematical calculations and console output; they lack network, file-writing, or code-execution capabilities.
- Sanitization: Input values are converted to specific numeric types or strings, preventing common injection vectors into the script logic.
Audit Metadata