social-listening

Warn

Audited by Socket on Oct 14, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The stated purpose is coherent with the read-only social-listening actions, but the trust model is weak: the skill depends on a third-party MCP endpoint and a transitive plugin install from a lightly established GitHub repo. Capabilities are mostly proportionate, yet the external mediation, shell access, and install chain raise medium-high security risk without clear evidence of outright malware.

Confidence: 86%Severity: 74%
Audit Metadata
Analyzed At
Oct 14, 2026, 11:00 AM
Package URL
pkg:socket/skills-sh/un-seen%2Fhedwigai-skills%2Fsocial-listening%2F@fb991452ce09a7faa20b2510dca63f586047d0299edae77dfd09350704e1b8ff