T08 · Insecure Dependencies
Warning
- Location
SKILL.md:163- Finding
Unpinned and Unverifiable Third-Party Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Rss Reader Ai Free
Security checks for vulnerabilities and agentic risk
Overview
This looks like an RSS summarization skill, but it needs review because it combines external AI/notification data flows with broad activation wording and unaudited Python setup instructions.
Install only in an isolated environment after obtaining and reviewing the missing implementation files and pinned dependencies. Use it with non-sensitive feeds unless you are comfortable sending article content, metadata, summaries, and notification details to the configured LLM and push providers, and narrow activation to explicit RSS aggregation tasks.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The description states that the skill generates Chinese summaries by default, and multiple sections reinforce Chinese-only output as the expected behavior. This is a locale/language policy concern because the skill imposes a specific output language without making it an explicit user choice or opt-in in the natural-language description.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill describes summarization and push delivery but does not clearly warn that fetched article content and metadata may be sent to third-party LLM providers and notification platforms. This creates a real data handling and privacy risk because users may supply private, internal, or sensitive feed sources without understanding that content leaves the local environment.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger condition '需要AI模型调用、智能对话、Agent编排、LLM应用时使用' is so broad that many unrelated requests could invoke this skill unintentionally. In a skill with network fetching, external API calls, and notification delivery, accidental activation can cause unreviewed data collection, outbound transmission, or message sending without clear user intent.
- Content