Back to skill

Security audit

SYRI 共线性分析

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese SYRI genome-analysis guide; its main risk is unpinned bioinformatics software installation, not hidden or malicious behavior.

Install only in a dedicated Conda or virtual environment, avoid running the commands as root, pin package versions or reviewed commits where possible, and review resource settings before launching high-thread or background alignment jobs.

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:16
Finding

Unpinned and Unverified Third-Party Dependencies

Content
View full analysis
Remediation
View remediation
``` 5. Verify the checked-out commit or release artifact using a trusted signature or independently published checksum before running `make`. 6. Review and lock transitive dependencies, not only the four directly named tools. 7. Perform installation in a dedicated, non-privileged virtual or Conda environment. Do not run installation or build commands as root. 8. Where practical, build dependencies in a restricted container or sandbox with limited filesystem access and no access to production credentials. 9. Periodically update pinned versions through a controlled process that includes source review, integrity verification, and compatibility testing. ]]>
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 file consistently presents all user-facing instructions in Chinese, which effectively forces a specific language for skill use. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific.

Content

No source excerpt is available for this finding.