browser-extract
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local terminal commands via
npxto fetch and store template states using@claude-flow/climemory operations. - [INDIRECT_PROMPT_INJECTION]: The skill inherently exposes an ingestion surface by scraping untrusted third-party web content. However, it explicitly mitigates this threat surface by implementing mandatory
aidefence_is_safeandaidefence_has_piiinspection steps prior to data persistence or model ingestion.
Audit Metadata