Back to skill

Security audit

RFP Response Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill performs limited local processing, but its scores are too simplistic to establish whether an RFP response is complete.

Review every answer and supporting document yourself; scores measure field values rather than actual compliance. Remove the template's initial comment lines before using the CSV parser, and independently verify procurement guidance. The optional Windows app requires a separate trust decision; this verdict does not cover that executable ([publisher repository](https://github.com/rapidworker1/Multiple-AI-models-Toolkit)).

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code implements a basic weighted row-ranking utility rather than the declared response-building and review workflow. Nonempty text receives the same score regardless of meaning, so an unanswered or noncompliant status can score like a satisfactory one. Although scoring requirement-matrix rows supports part of the declared purpose, response generation and reviewer flagging are absent. Local CSV reading and report writing are ordinary supporting operations; no unrelated access or external communication is shown.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.