task-intelligence
Warn
Audited by Socket on Mar 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose is coherent for a planning/orchestration skill, but it materially broadens the agent’s scope by routing tasks through multiple other skills and agent outputs. Main risk is transitive trust and indirect prompt-injection via ecosystem orchestration, not overt malware or credential theft.
Confidence: 82%Severity: 56%
Audit Metadata