ClawHub
Back to skill

Security audit

Academic Deep Research Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed web-research workflow skill with user checkpoints, not an installer or privileged local execution package.

Install this if you want a structured, citation-heavy research workflow. Do not use it with confidential topics unless you are comfortable with web searches and fetched third-party pages reflecting the research subject; review the generated plan before approving execution, especially if it proposes broad searches or parallel sub-agents.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README explicitly advertises broad trigger phrases like "deep research on" and "exhaustive analysis of," which can cause the platform to invoke this powerful research skill in response to generic user language rather than deliberate tool selection. Because the skill performs web-based investigation and multi-step autonomous actions, accidental invocation can lead to unintended browsing, data exposure through searches/fetches, or surprising agent behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README describes automatic use of web_search and web_fetch during execution but does not warn users that their prompts, topics, or derived queries may be transmitted to external web resources or that fetched content may come from untrusted sites. In a research skill, this omission is significant because users may provide sensitive topics, proprietary questions, or internal context, assuming the process is effectively local or "offline."

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation guidance says to trigger the skill for 'deep research, exhaustive analysis, or literature review' and similar broad intents without giving exclusion criteria or negative examples. Terms like 'analysis' and 'research' are common across many user requests, which could cause the skill to be invoked in situations where a narrower or different skill would be more appropriate.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The explicit 'Auto-Execute' phase authorizes the skill to proceed with multiple web_search and web_fetch actions without an additional user confirmation at execution time. In a research skill that may visit many external sources and accumulate sensitive context, this weakens user control, can trigger unintended external requests, and increases the chance of over-collection or policy-breaking autonomous behavior.

Content

Scanner excerpt · example.md (reported line 76)May include surrounding context.

md
---

## Phase 3: Research Cycles (Auto-Execute)

### Theme 1: Market Landscape — Cycle 1

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation guidance includes broad natural-language triggers such as mentioning "deep research" or "exhaustive analysis," which can match ordinary user conversation rather than an intentional skill invocation. In an agent environment, this can cause unintended activation of a high-autonomy research workflow, leading to unexpected tool use, extra cost, scope expansion, or processing of sensitive topics without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file requires 'APA citations throughout,' which imposes a specific formatting convention regardless of user preference. This is a natural-language policy concern because it forces a style choice without offering the user an option or documenting why that locale/style constraint is necessary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.