T09 · Insecure Skill Coding Practices
Error
- Location
summarize.py:76- Finding
Unrestricted URL Fetching Enables Server-Side Request Forgery
- Content
View full analysis
- Remediation
View remediation
Security audit
Summarize
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent summarizer, but its URL mode can fetch arbitrary addresses without safeguards, which needs review before installation.
Install only if you are comfortable with a summarizer that can read user-specified local files and fetch user-specified URLs. Avoid using it with secret files, private/internal URLs, URLs containing credentials or tokens, or in environments that can reach sensitive internal services unless URL validation or network egress controls are added.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
The skill advertises capabilities that imply local file reading and outbound network access, but it does not declare any explicit tool scope or permission boundaries. This creates a confused-deputy risk where an agent may fetch URLs or read files without clear user consent, increasing the chance of unintended data exposure from local documents or remote requests.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
The natural-language description and usage guidance are entirely in Chinese, while the metadata claims
多语言支持（中文/英文）. This can be read as forcing a specific language for interaction or documentation without explicit user opt-in or a clear language-selection mechanism.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This code sets a fixed UTF-8 stdout wrapper and presents its docstrings and user-visible status/error text in Chinese, establishing a specific language/locale behavior with no user opt-in or alternate locale support. Under the policy, forcing a specific language without user choice is a natural-language policy violation.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The markdown states that providing a URL will automatically fetch webpage content, but it does not warn users that this triggers an external network request or explain any privacy implications. Users may unknowingly cause requests to third-party sites or send sensitive internal URLs, which can leak browsing intent, tokens in URLs, or internal resource locations.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The manifest description is written entirely in Chinese and does not indicate any user choice of language or locale. This can conflict with language/locale policy requirements when a skill implicitly assumes one language without documenting opt-in or regional scope.
- Content
Static analysis
No suspicious patterns detected.