social-media-post
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes vendor-authorized CLI tools (
dumplingai) to perform research and source extraction tasks. - [SAFE]: Data processing is localized to a specific directory (
.dumplingai/), and there are no signs of unauthorized network operations or data exfiltration. - [SAFE]: The safety rules proactively address the risk of indirect prompt injection by explicitly stating that source material from scraped pages or transcripts is untrusted and that embedded instructions must be ignored.
Audit Metadata