Back to skill

Security audit

捷帮文件处理

Security checks for vulnerabilities and agentic risk

Overview

This skill performs the advertised conversions, but it sends all submitted content and an environment-based admin key to an external service for tasks that could be done locally.

Review this carefully before installing. Do not use it with passwords, tokens, private URLs, proprietary files, or regulated data unless you are comfortable sending that content to the external JieBang service and using the configured admin credential. A local-only implementation would be safer for these operations.

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)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/main.py:16
Finding

Sensitive Input Is Transmitted to an External Service for Locally Performable Operations

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (11)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill retrieves an admin credential from the environment and attaches it to every external API request, despite only offering basic text transformations. Using a privileged key for low-risk utility operations broadens the blast radius if the endpoint, logs, or surrounding service are compromised.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is described as a local text/file processing utility, but it sends the full user-provided input to an external domain for hashing. This creates an undisclosed data exfiltration path for potentially sensitive text and violates user expectations that these simple operations occur locally.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises externally backed processing but does not declare any explicit tool scope or permissions despite detected network and environment capabilities. This weakens least-privilege controls and makes it harder for reviewers and users to understand what the skill can access, increasing the risk of unintended outbound requests or broader data exposure if the implementation is modified or abused.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description says it is based on an external API, but it does not clearly warn users that submitted text or file-derived content will be transmitted off-platform for processing. This creates a privacy and data-handling risk because users may provide secrets, personal data, or proprietary content under the assumption processing is local.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module documentation claims the tool provides hashing, Base64, and URL functions directly, but the implementation is actually a proxy to an external API. This mismatch misleads reviewers and users about where their data goes and masks the real trust boundary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The code sends raw user input to an external API without any user-facing warning, despite handling content that may include secrets, URLs with tokens, or confidential text. Lack of disclosure prevents informed consent and increases the risk of inadvertent sensitive-data leakage.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Base64 encoding/decoding is a local primitive, yet the code transmits all input to a remote API. Users may paste secrets, tokens, or files for conversion, so this behavior unnecessarily exposes sensitive content to a third party.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

URL encoding/decoding can be safely performed locally, but this implementation sends user input to an external service. That creates unnecessary exposure of URLs, parameters, tokens, and other potentially sensitive data embedded in the input.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing natural-language content in the skill file is in Chinese, with no indication that the skill supports other languages or that Chinese is a justified locale-specific requirement. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The human-readable descriptions and user-facing strings are written only in Chinese, with no indication that the user can choose another language or locale. Under the policy rule, a skill should not impose a language/locale without opt-in unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The script retrieves an admin key from an environment variable and injects it into the X-Admin-Key request header, but there is no user-facing notice that credentials are required and will be used for outbound authentication. This is a safety-relevant behavior under the warning criteria for code files because it accesses sensitive environment-based credentials silently.

Content

No source excerpt is available for this finding.