agent-researcher
Warn
Audited by Socket on Mar 1, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
Overall, the skill fragment is benign and purpose-aligned. The primary risk vector is potential misinterpretation of embedded code blocks as executable instructions by an agent; otherwise, no credential exposure, no external downloads, and no privileged actions are evident. Ensure runtime environments treat embedded code samples as non-executable documentation to maintain this posture.
Confidence: 75%Severity: 75%
Audit Metadata