mercury
What this skill does
Financial management and payment processing via Mercury API
github/mvanhorn - Privilege Escalation - 1.9k stars
Threat analysis
Skill info
pkg:github/mvanhorn/printing-press-library@5a78746?skill=mercuryAssessments (2)
Privilege Escalation
Privilege Escalation via local-llm-review
README.md
The install instructions include `npx -y @mvanhorn/printing-press-library install mercury` which could potentially execute arbitrary code if the package is compromised.Obfuscation
Obfuscation via local-llm-review
.goreleaser.yaml
The ldflags parameter includes `-X github.com/mvanhorn/printing-press-library/library/payments/mercury/internal/cli.version={{ .Version }}` which could be used to inject arbitrary values during the buBadge
Add the Anomity scan badge for mercury to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of mercury? Report an issue or request a rescan.
