ClawHub
Back to skill

Security audit

Akashic Deep Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward research helper that uses disclosed Akashic web and deep-research tools, with a minor caution that its activation triggers are broad.

Install this if you want an Akashic-backed research assistant. Be mindful that broad research wording may activate it, and avoid including private or sensitive information in research prompts unless you are comfortable sending that context to the configured external research/search tools.

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
  • 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
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases are broad, generic verbs like 'research', 'investigate', 'look into', and 'study', which can match many ordinary user requests and cause the skill to activate unintentionally. Because this skill can invoke web and deep-research tools, accidental invocation may lead to unnecessary external queries, unintended data exposure in prompts, or execution of a more powerful workflow than the user expected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.