ClawHub
Back to skill

Security audit

citation-competitor-intelligence

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only research workflow for finding deep-tech competitors through public academic, patent, and company sources, with no hidden execution or persistence behavior found.

Install only if you need academic/deep-tech competitor research. Use it with public, lawfully obtained sources, avoid collecting unnecessary personal details about researchers, and verify company, patent, and funding claims before relying on them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger examples are broad and do not define activation boundaries, which can cause the agent to invoke this skill in contexts that were not intended, such as generalized competitor research or sensitive profiling tasks. In a skill that performs intelligence gathering on researchers, companies, and commercialization activity, over-broad routing increases the chance of misuse, privacy-invasive analysis, or low-relevance autonomous actions.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The checklist directs users to collect and correlate identifiable individuals' company roles, ownership, executive status, funding, and commercialization details without any privacy, legality, or data-minimization guardrails. In a competitor-intelligence skill, this increases the likelihood of invasive profiling, misuse of personal data, and collection beyond what is necessary for legitimate research.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/workflow.md (reported line 31)May include surrounding context.

md
**Operations**:
1. Extract all references from the anchor paper:
   - Semantic Scholar API: `https://api.semanticscholar.org/graph/v1/paper/{paper_id}/references`
   - Google Scholar: "Cited by" section → manually review
   - Web of Science: Cited References
2. Focus on references that are:

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/workflow.md (reported line 51)May include surrounding context.

md
**Operations**:
1. Extract all references from the anchor paper:
   - Semantic Scholar API: `https://api.semanticscholar.org/graph/v1/paper/{paper_id}/references`
   - Google Scholar: "Cited by" section → manually review
   - Web of Science: Cited References
2. Focus on references that are:

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
67% confidence
Finding

The document is bilingual, but it does not specify whether the skill will respond in the user's preferred language or how that preference is determined. This can create a mild language-policy concern if the skill defaults to one language without explicit user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The title and body include bilingual terminology and Chinese-only names/labels, but the document does not state that the skill supports multiple languages by user choice or that it is intended for a Chinese-language audience. Under the policy rule, forcing or assuming a specific language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase '法定代表人/股东/高管' forces a specific language in an otherwise English document and does not provide an English equivalent or indicate that Chinese terminology is optional or required for a region-specific workflow. This is a natural-language locale policy issue because users are not given a language choice or context for the language switch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction explicitly prescribes Chinese search terms ("融资" and "创业") as part of the workflow. This imposes a language/locale choice in natural-language guidance without stating that the workflow is China-specific or offering the user an alternative language option.

Content

No source excerpt is available for this finding.