Incomplete referenced artifact analysis
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/atsprep.mjs <tool> key=value key=@path/to/file.txt
Security audit
ATSPrep: Resume ATS check
Security checks for vulnerabilities and agentic risk
Overview
The skill provides resume checks through ATSPrep with disclosed data sharing and no evidence of hidden access or harmful actions.
Use this skill if you are comfortable sending your resume text to ATSPrep. Optional AI tools also share relevant text with Cloudflare. Remove unnecessary personal details, delete temporary files, and keep ATSPREP_MCP_URL unset unless you intentionally trust another endpoint. The bundled files do not independently verify the service's privacy promises.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)
Incomplete referenced artifact analysis
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md n the current working directory first, and delete it when you're done. `node scripts/atsprep.mjs list` lists the tools.
Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Unrestricted Tool Access
Medium
- Category
- Excessive Agency
- Confidence
- 80% confidence
- Finding
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
- Content
ATSPrep MCP tools
Endpoint:
https://atsprep.com/mcp(MCP streamable HTTP, no auth). Call any tool with:sh node scripts/atsprep.mjs <tool> key=value key=@file.txt
The skill exposes resignation-letter drafting and notice-period calculation, which are unrelated to its stated resume ATS-checking purpose.
Low
- Category
- Excessive Agency
- Confidence
- 97% confidence
- Finding
L158–L175 instruct the agent to use draft_resignation_letter to generate resignation letters and calculate a last working day from notice periods. These capabilities neither score a resume nor help explain or fix its ATS issues, and the manifest does not declare broader employment-management assistance.
- Content