deep-research-pro
Warn
Audited by Socket on Apr 19, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the core purpose is coherent for a research skill, but execution trust is weakened by undeclared local helper dependencies, unclear publisher/source verification, and third-party distribution links. The largest operational risk is indirect prompt injection from arbitrary web content combined with agent write capability; there is no strong evidence of credential theft or confirmed malware.
Confidence: 84%Severity: 64%
Audit Metadata