ClawHub
Back to skill

Security audit

bangumi-explorer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Bangumi lookup helper that makes expected API requests and stores short-lived local cache files for faster results.

Install this if you are comfortable with a skill making unauthenticated requests to Bangumi and caching fetched results in ~/.bangumi/cache/. Avoid using it on shared machines if local query/result traces are sensitive to you.

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
  • 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
93% confidence
Finding

The skill instructs use of code execution, network access, and local caching, but it does not declare tool scope or permissions. This weakens least-privilege controls and transparency, making it easier for an agent to invoke broader capabilities than a user or platform reviewer would expect.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
# === 常量 ===

BASE_URL = "https://api.bgm.tv/v0"
HEADERS = {"User-Agent": "MountLynx/bangumi_skill (https://github.com/MountLynx/bangumi_skill)"}
TYPE_MAP = {
    "anime": 2, "book": 1, "game": 4,

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · bangumi.py (reported line 28)May include surrounding context.

python
# === 常量 ===

BASE_URL = "https://api.bgm.tv/v0"
HEADERS = {"User-Agent": "MountLynx/bangumi_skill (https://github.com/MountLynx/bangumi_skill)"}
TYPE_MAP = {
    "anime": 2, "book": 1, "game": 4,

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · bangumi.py (reported line 755)May include surrounding context.

python
# === 常量 ===

BASE_URL = "https://api.bgm.tv/v0"
HEADERS = {"User-Agent": "MountLynx/bangumi_skill (https://github.com/MountLynx/bangumi_skill)"}
TYPE_MAP = {
    "anime": 2, "book": 1, "game": 4,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill notes that it caches API responses under ~/.bangumi/cache/ but does not clearly warn users in the description or safety metadata that local files will be written. Undisclosed filesystem writes can surprise users, create persistence on shared systems, and expose query history or fetched content to other local users/processes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.