app-store-optimization
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from external sources, such as user reviews and competitor metadata, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the agent context through the
reviewsparameter inscripts/review_analyzer.pyand theapp_dataparameter inscripts/competitor_analyzer.py. - Boundary markers: The skill's instructions and scripts do not implement explicit boundary markers or instructions to ignore embedded commands within the processed data.
- Capability inventory: Across all modules (
keyword_analyzer.py,metadata_optimizer.py,competitor_analyzer.py,aso_scorer.py,ab_test_planner.py,localization_helper.py,review_analyzer.py,launch_checklist.py), there are no instances of subprocess calls, dynamic code execution (exec/eval), file system writes, or network operations. - Sanitization: The scripts utilize regex for text normalization but lack dedicated sanitization to filter or escape natural language instructions found in external content.
Audit Metadata