ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill is explicitly about Ramp (a corporate spend/financial platform) and enumerates concrete money-moving and account-management actions—issuing/configuring cards, funding cards, initiating/approving purchases, transfers, vendor payments, and changing accounting/treasury settings. Although it enforces Paperclip approval gates and forbids autonomous execution, the skill's primary and explicit domain is financial operations (Ramp-specific actions). That meets the criteria for Direct Financial Execution authority.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The REQUIRED workflow explicitly fetches outsider-authored Ramp instructions (public web content) at runtime via the `curl` command in `SKILL.md`, which are then read and incorporated into the agent’s LLM context; i.e., injected free text could come from `https://agents.ramp.com/.../SKILL.md` or playbook pages.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly requires fetching Ramp's live instructions at runtime (e.g., https://agents.ramp.com/.well-known/agent-skills/get-started/SKILL.md as shown in the curl example) and uses that fetched content as authoritative runtime instructions that will control the agent's behavior.
- Repository
- paperclipai/paperclip
- Commit
14f20be
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.