ClawHub
Back to skill

Security audit

AlgoDocs

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AlgoDocs connector skill that uses the OOMOL oo CLI for account-scoped reads and one confirmed write action, with no evidence of hidden or destructive behavior.

Install this only if you intend to let an agent use your connected AlgoDocs account through OOMOL. Review any proposed upload or other write payload before approval, and avoid using it for vague mentions of AlgoDocs when you only want general information.

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
92% confidence
Finding
The description says to use this skill for ANY AlgoDocs request and whenever a task involves AlgoDocs, instead of calling the API directly. That broad trigger can cause the agent to invoke the skill on mere mention of AlgoDocs, including ambiguous, informational, or attacker-planted references, increasing the chance of unintended external actions or premature tool use.

Static analysis

No suspicious patterns detected.