Back to skill

Security audit

Canopy

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly discloses that it enables policy-gated organizational payments, but users should treat it as sensitive because it can move funds through Canopy.

Install only if you intentionally want an agent connected to Canopy to spend organizational funds. Use the least-privileged Canopy agent, strict spend caps and allowlists, verify recipient and amount before payments, and do not let the agent approve pending payments without a clear user instruction.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
---
name: canopy
description: |
  Canopy treasury wallet for AI agents — make policy-gated USD payments on-chain (Base), auto-pay paywalled APIs (x402 / MPP), and discover paid services. Every payment passes through the agent's policy: spend cap, recipient/service allowlist, and approval threshold. Payments above the threshold return pending_approval and wait for a human; payments outside the cap or allowlist return denied. Install only if your agent needs to spend org funds. Connect with the least-privileged agent + policy available, verify recipient and amount before each canopy_pay, and never auto-approve on the user's behalf.
  Requires a Canopy account at https://www.trycanopy.ai. After install, configure the canopy MCP server with your CANOPY_API_KEY and CANOPY_AGENT_ID from the dashboard.
metadata:
  author: canopy

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
---
name: canopy
description: |
  Canopy treasury wallet for AI agents — make policy-gated USD payments on-chain (Base), auto-pay paywalled APIs (x402 / MPP), and discover paid services. Every payment passes through the agent's policy: spend cap, recipient/service allowlist, and approval threshold. Payments above the threshold return pending_approval and wait for a human; payments outside the cap or allowlist return denied. Install only if your agent needs to spend org funds. Connect with the least-privileged agent + policy available, verify recipient and amount before each canopy_pay, and never auto-approve on the user's behalf.
  Requires a Canopy account at https://www.trycanopy.ai. After install, configure the canopy MCP server with your CANOPY_API_KEY and CANOPY_AGENT_ID from the dashboard.
metadata:
  author: canopy

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes broad terms like "pay", "approve", "deny", and "budget" that can appear in ordinary conversation, increasing the chance this high-risk payment skill is invoked when the user did not intend to initiate treasury actions. Because the skill can move organizational funds or approve pending payments, accidental invocation in ambiguous contexts materially raises the risk of unintended financial operations.

Content

No source excerpt is available for this finding.