ClawHub
Back to skill

Security audit

Bluesky

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Bluesky connector that can read Bluesky data and create posts only after user confirmation.

Install this only if you want your agent to use OOMOL's oo CLI for Bluesky account actions. Review post text before approving any write action, and be aware that setup may install the oo CLI and sign in to an OOMOL account.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description and frontmatter instruct the agent to use this skill for ANY Bluesky request instead of calling the API directly, which is an overly broad trigger condition. This can cause the skill to activate in situations where a narrower or safer handling path would be more appropriate, increasing the chance of unintended reads or writes if the agent overroutes Bluesky-related tasks through this connector.

Static analysis

No suspicious patterns detected.