Back to skill

Security audit

pain-opportunity-radar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign because it found no reported malicious behavior, though the review is incomplete and confidence is medium.

The verdict is benign, but not risk-free. Skillspector's analysis is partial because it could not resolve a local path-like reference, so the evidence is incomplete. Consider whether the required Chinese and English query languages suit your research before installing.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The query-building workflow mandates Chinese and English by default without user opt-in.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The instruction selects two specific natural languages for research queries without offering the user a language choice. Although multilingual research is part of the skill's purpose, the skill is not restricted to a region or context that justifies requiring Chinese and English for every task.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.

md
- Do not infer that a local file is unpublished merely because it sits in a folder named `drafts`. The user’s confirmed release status, a CMS record, or a publication log is authoritative. Treat a published local source as the audit baseline and record the filename as storage metadata only.
- A prior fact-check report is a regression oracle, not proof that the current version is clean. Compare every historical P0/P1 item with the current published text.
- Separate event existence from causal attribution. A reported outage may be real while the claimed model behavior, permission path, or root cause remains disputed.
- Regulatory materials define jurisdiction-specific requirements. Do not compress them into universal prohibitions without checking the governing text.

## Failure handling