checkpoint
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose is coherent, and its requested tool scope is modest, but its trust-critical implementation depends on unverified executables (./run.sh and especially memory-agent) with undocumented provenance. Data storage in ArangoDB fits the stated goal, yet the actual data and credential path is obscured behind a CLI that could not be matched to an official, same-tool distribution. This is not confirmed malware, but it is high supply-chain risk and should not be treated as benign without validating the source of those binaries/scripts.
Confidence: 84%Severity: 80%
Audit Metadata