social-media-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides legitimate analytical functionality for social media managers. All processing occurs locally via standard Python scripts (
calculate_metrics.pyandanalyze_performance.py) which use basic arithmetic for metrics calculation. - [COMMAND_EXECUTION]: The skill uses Python scripts to process JSON input. This is a standard and safe use of the execution environment for data analysis.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file access or network operations to external domains were detected. The scripts only process the campaign data provided by the user in the input JSON.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied social media data (likes, comments, etc.). While this represents an ingestion surface, the data is strictly numerical or categorical (platform names, post IDs) and is processed by mathematical scripts rather than being directly interpolated into a prompt for LLM execution without boundaries. The potential for injection is negligible.
Audit Metadata