ramp
What this skill does
The skill 'ramp' is a Paperclip wrapper for Ramp's published agent playbooks, designed to fetch and follow Ramp's instructions with mandatory approval gates for financial actions.
github/paperclipai - Security Misconfiguration - 76.4k stars
Threat analysis
Skill info
pkg:github/paperclipai/paperclip@5a0985f?skill=rampAssessments (1)
Security Misconfiguration
Security Misconfiguration via local-llm-review
SKILL.md
The skill instructs agents to fetch instructions from external URLs (e.g., `https://agents.ramp.com/playbooks`) without verifying the integrity or authenticity of the fetched content beyond a discoverBadge
Add the Anomity scan badge for ramp 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 ramp? Report an issue or request a rescan.
