ClawHub
Back to skill

Security audit

Ravi passwords

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent password-manager skill that openly handles plaintext passwords, with the main caution being accidental exposure in command output, logs, or transcripts.

Install only if you are comfortable with the Ravi CLI and service handling website credentials. Treat every password command output as sensitive: avoid sharing transcripts, screenshots, terminal logs, copied snippets, and shell history that may contain returned passwords.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly states that users send and receive plaintext credential values, including passwords, but does not pair that with clear warnings about sensitive-output handling, terminal history, logs, screenshots, and downstream tooling exposure. In a password-manager skill, normalizing plaintext retrieval without operational safeguards increases the chance that secrets are leaked through routine agent or shell usage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The examples demonstrate storing credentials in shell variables and retrieving full password records via list/get flows without warning that these values may be exposed in command output, shell history, process inspection, logs, or agent transcripts. Because the examples are likely to be copied verbatim, they operationalize insecure secret handling and make accidental credential disclosure substantially more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.