ClawHub
Back to skill

Security audit

Agent Credential Vault - Anima

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed credential-vault guide for letting agents use secrets through Anima, with some sensitive reveal commands that users should treat carefully.

Install only if you are comfortable trusting Anima to store and broker credentials for agents. Prefer brokered reveal policies and allowed-host restrictions, use dry-run before exec, and avoid `vault get` or `vault totp` unless a human intentionally needs the raw value because those outputs can enter terminal history, logs, traces, or agent context.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly documents commands that return raw credential material or active TOTP codes to the caller, but it does not pair them with a clear warning that doing so exposes secrets to the agent context, terminal output, logs, traces, and downstream tooling. In a skill whose core security claim is that agents can use secrets without seeing them, presenting `get` and `totp` as routine capabilities without strong guardrails materially increases the chance that users will accidentally bypass the safer brokered model.

Static analysis

No suspicious patterns detected.