csv-formula-injection
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. This skill is internally consistent as a CSV formula-injection testing guide and shows no supply-chain, credential-harvesting, or hidden exfiltration by the skill itself. However, it equips an AI agent with concrete offensive payloads, obfuscation methods, and exfiltration primitives, creating high security risk even with authorization caveats.
Confidence: 88%Severity: 78%
Audit Metadata