research-lookup
Warn
Audited by Socket on Apr 21, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is mostly coherent with its stated research purpose and uses an official Parallel endpoint, but it expands trust through undisclosed local scripts and an OpenRouter intermediary for academic searches. Credential scope is proportionate and there is no clear malicious behavior, yet the combination of external content ingestion, Bash/Write capability, transitive skill references, and third-party routing makes the overall risk moderate.
Confidence: 87%Severity: 56%
Audit Metadata