aso-daily-report
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/appmate_config.py,scripts/aso_daily.py, andscripts/aso_optimize_v2.py) to perform metadata analysis and report generation. This is standard behavior for an AI agent skill.\n- [EXTERNAL_DOWNLOADS]: The skill queries the official iTunes Search API to fetch real-time keyword rankings. As a well-known service, this communication is expected and necessary for the tool's primary purpose.\n- [DATA_EXFILTRATION]: The skill interacts with local data files in thedata/directory, including app lists and sales snapshots. It requires App Store Connect credentials, which are verified through a local configuration script. No unauthorized data exfiltration to external domains was observed.\n- [PROMPT_INJECTION]: The skill ingests raw App Store metadata which is then processed by the LLM for tokenization. While this represents a potential surface for indirect prompt injection, it is considered safe in this context.\n - Ingestion points: App metadata is loaded from
data/apps_full.jsonin Step 2.\n - Boundary markers: None identified.\n
- Capability inventory: Subprocess execution of Python scripts (
scripts/*.py) and file writing todata/aso_daily.md.\n - Sanitization: None identified in the prompt instructions.
Audit Metadata