agentic-development
Warn
Audited by Socket on May 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS rather than benign: the stated purpose matches a broad orchestration skill, and there is no evidence of external installers, credential harvesting, third-party gateways, or obvious exfiltration. However, the skill has a wide action surface, includes release/deploy and autonomous loop orchestration, and explicitly tells the agent to install companion skills if missing, creating transitive trust risk. The main concern is scope and autonomy, not confirmed malicious behavior.
Confidence: 88%Severity: 52%
Audit Metadata