social-fetch
Warn
Audited by Socket on Oct 1, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s overall purpose is coherent and the scanner’s command-injection findings are false positives, but the optional fallback architecture routes requests and provider credentials through third-party scraping services rather than official platform APIs. That is a meaningful data-flow and trust risk, especially with the unverified 'agent-browser' component, though there is no clear evidence of malware or deceptive hidden behavior.
Confidence: 91%Severity: 58%
Audit Metadata