Back to skill

Security audit

百积木 Hosted Service 开发

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Baijimu deployment guide, with a supply-chain caution because it installs an unpinned CLI package.

Install this only if you intend to use Baijimu Hosted Service workflows and are comfortable granting the Baijimu CLI deployment access to the relevant workspace, project, environments, and migrations. Prefer a pinned or otherwise verified @baijimu/cli version in production-sensitive environments, and confirm credentials are least-privileged before running deployment or migration commands.

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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:13
Finding

Unpinned npm CLI Dependency Creates a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation
" bins: [baijimu] ``` 2. Use a lockfile and registry-supported integrity hashes where the Skill installation mechanism supports them. 3. Verify package provenance, publisher ownership, signatures, and release attestations before approving upgrades. 4. Route dependency upgrades through code review and automated security scanning. 5. Disable npm lifecycle scripts during installation when they are not required; if they are required, review them before deployment. 6. Install and execute the CLI with a least-privileged account that does not unnecessarily expose production credentials. 7. Keep deployment credentials short-lived and scoped to only the required workspace, project, and operations. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is entirely in Chinese and provides no indication that another language is available. This can violate a language/locale policy when users are not given an explicit choice or opt-in for Chinese-only interaction.

Content

No source excerpt is available for this finding.