ClawHub
Back to skill

Security audit

Sports Science Daily

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed sports-science news aggregation workflow that uses expected external APIs and cloud exports for its stated purpose.

Install only if you are comfortable with the workflow fetching public sources, sending content for translation, and creating/sending reports through Feishu and optionally Notion using your configured credentials. Review recipient IDs and language settings before running.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly states it sends data to multiple third-party services including Google Translate, Feishu, Notion, PubMed, and various RSS sources, but the usage instructions do not clearly warn users that running the skill transmits fetched content and integration metadata outside the local environment. This is a real transparency and privacy issue because users may invoke the skill assuming it is only aggregating locally, when it actually performs external network calls and publishes output to external platforms.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Defaulting the skill to translate all content to Chinese without explicit user opt-in can cause unintended disclosure of fetched material to the translation provider and may produce outputs in a language the user did not request. In this skill's context, the issue is less about direct exploitability and more about consent, data handling transparency, and potentially surprising behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.