web-research
Warn
Audited by Socket on Aug 26, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s purpose and capabilities mostly align, and it does not request credentials or install software. The main risk is indirect prompt injection: it directs broad consumption of untrusted web content and synthesis into deliverables, which is high-risk if paired with powerful agent tools.
Confidence: 92%Severity: 62%
Audit Metadata