launch-retro-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration behaviors were detected in the skill instructions.
- [DATA_EXPOSURE]: The skill processes marketing analytics and launch performance data (e.g., GA4 UTM exports). This behavior is consistent with its stated purpose as a retrospective analyzer and relies on local vendor-provided scripts (such as registry-events.py) for structured data handling.
- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted external data including CSV exports, dashboard screenshots, and comment threads. It proactively mitigates the risk of indirect prompt injection by including explicit instructions to treat all such data as untrusted and to disregard any commands or instructions embedded within those files.
Audit Metadata