Back to skill

Security audit

interview-answer-forge

Security checks for vulnerabilities and agentic risk

Overview

The skill stays within its interview-coaching purpose, with disclosed local storage and minor cautions about privacy and a generated command shortcut.

Keep confidential employer or customer details out of the plaintext story bank, and back it up before modifying it. Use scripts/interview_forge.py and export stories to JSON for scoring instead of copying the generated inline shell shortcut. Inspection resolved the scanner's missing-file gap; host runtime permissions were not independently verified.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: interview-answer-forge
description: "Use when preparing for a job interview with a JD and your background — turns the STAR method from vague advice into a build system: mines your history for evidence, generates question-predictions from the JD, drafts STAR stories with a weak-spot flag on every answer, and pressure-tests with follow-up chains."
version: 1.0.0
author: Denis Voronin
license: MIT
tags: [interview, career, star-method, job-search, preparation]
---

# Interview Answer Forge

## Overview

"Use STAR" is the most given and least executed interview advice in existence. People are told to structure answers

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/forge-guide.md (reported line 64)May include surrounding context.

md
- The bug/incident/outage you'll never forget
- The scope you cut to hit a date — what you cut and why it was right

Each answer is one bank line. Don't judge quality while mining; judge coverage after.

## Answering the salary question (early rounds)

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.