ClawHub
Back to skill

Security audit

DefiLlama OpenAPI Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only DefiLlama API helper with a disclosed setup flow, though users should prefer a pinned or local schema source.

Before installing, consider changing the setup to use the bundled schema or a schema URL pinned to a specific commit. Avoid treating this skill as wallet, trading, admin, or authenticated DefiLlama Pro tooling.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:35
Finding

Mutable Remote OpenAPI Schema Bypasses the Audited Bundled Schema

Content
View full analysis
Remediation
View remediation
/skills/defillama-openapi-skill/references/defillama-public.openapi.json ``` 3. Publish and verify a cryptographic digest, such as SHA-256, before passing a downloaded schema to UXC. Fail closed if verification does not succeed. 4. Update both `SKILL.md` and `references/usage-patterns.md` so all documented workflows use the same pinned or local schema source. 5. Extend `scripts/validate.sh` to reject schema URLs containing mutable branch references such as `/main/` and to verify that documented remote references use an approved commit and expected digest. 6. Review schema updates through the same security process as package code, including confirmation that only the intended HTTPS server and read-only operations are present. ]]>

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep