ClawHub
Back to skill

Security audit

RSS AI 摘要 LITE

Security checks for vulnerabilities and agentic risk

Overview

This skill openly describes fetching RSS feeds, summarizing them with an LLM, posting summaries to Feishu, and storing local deduplication data, with the main caution being to review any separate code it asks you to run.

Install only if you are comfortable sending selected feed content and generated summaries to your configured LLM backend and Feishu webhook, and allowing a local SQLite database for deduplication. Because the artifact does not include the Python implementation it asks you to run, review the separate project code and dependencies before providing API keys or webhook URLs.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description is broadly scoped to handle generic 'rss ai reader' tasks and to be invoked by arbitrary agent platforms without clear trigger constraints or execution guardrails. In an agent environment with exec capability, vague activation criteria can cause the skill to be selected in contexts where users did not explicitly consent to network fetching, summarization, webhook delivery, or local state changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly performs external transmission to a Feishu webhook and persistent local storage in SQLite, but the user-facing description does not prominently warn that feed content and LLM-generated summaries will leave the local context and that identifiers will be retained on disk. This can lead to unintentional disclosure of sensitive feed data or unexpected persistence when the skill is run through an agent that abstracts these operations from the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The line states that summaries are always output in Chinese regardless of the original language. This is a natural-language policy issue because it forces a specific locale/language behavior without offering user choice or documenting opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The documentation instructs users to supply API keys and webhook URLs via environment variables but does not include handling guidance for these secrets. In practice, users may place secrets into configs, logs, screenshots, shell history, or shared agent sessions, increasing risk of credential leakage and unauthorized webhook use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.