Back to skill

Security audit

yzy1

Security checks for vulnerabilities and agentic risk

Overview

This skill locally scores survey spreadsheets and writes a new scored file, with no evidence of network access, persistence, credential use, or deceptive behavior.

Install only if you are comfortable giving the skill local read access to the spreadsheet you choose and allowing it to create a scored CSV/XLSX output file. Review the output path, especially if a `_scored` file already exists, and avoid using it on sensitive questionnaire data unless local processing is acceptable.

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
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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content, including the description, argument hints, feature list, and usage instructions, is presented only in Chinese. Per the policy, forcing a specific language without user opt-in or an explicit justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file describes that the tool will automatically generate a _scored file, which is a file-writing operation affecting user data. Under the markdown-specific warning criterion, the description should explicitly disclose this behavior as a user-impacting action rather than only mentioning it as an output format detail.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.