dryad
Warn
Audited by Socket on Sep 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's capabilities mostly match its stated purpose and data stays local, but trust in the required `de-novo`/Grove CLI chain is not clearly verifiable from the provided evidence. The `eval` examples are launcher convenience patterns, not remote download-execute, and the autonomy/stealth finding appears unfounded; however, the unverifiable external CLI dependency makes the install/execution trust disproportionate enough to keep risk high.
Confidence: 84%Severity: 72%
Audit Metadata