Back to skill

Security audit

interview-me

Security checks for vulnerabilities and agentic risk

Overview

The skill is a review concern because it presents itself as an interview helper while requesting broad read and command-execution tools and documenting vague automation, API, file, and command workflows.

Review this before installing. The artifact does not show exfiltration, destructive code, or persistence, but it asks for powerful read and command-execution capability while its purpose and operating boundaries are unclear. Install only if you are comfortable granting those tools to this skill, or require the publisher to remove exec/read or document exact scoped operations and consent requirements.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:16
Finding

Excessive File-Read and Command-Execution Permissions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest presents this as a narrow intent-elicitation interview skill, but the body describes broad automation, data processing, workflow orchestration, and GitHub/API-backed operations. This mismatch can mislead users and policy engines into granting trust or capabilities under false pretenses, increasing the risk of unexpected data access or execution paths.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Declaring the 'exec' capability for a skill whose stated purpose is only to ask one clarifying question at a time violates least privilege. If the platform enables this tool, the skill could execute local commands unnecessarily, creating avoidable risk of command execution, file access, or chained abuse through prompt steering.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation expands the skill into API credential setup, file handling, network/API calls, and command execution despite no legitimate need for those actions in an intent-interview workflow. This broadens the operational surface and normalizes sensitive behaviors that could expose credentials, touch local files, or run commands under the guise of a harmless clarification tool.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger condition 'when the user needs to perform related operations' is so broad that the skill could activate in many unrelated contexts. Overbroad activation increases the chance that a privileged or misleadingly documented skill is invoked without clear user intent, enabling unnecessary access or execution opportunities.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file claims a one-question-at-a-time intent extraction behavior, but most of the content documents generic automation and processing features instead. This inconsistency increases the likelihood of deceptive or confusing deployment, where reviewers and users underestimate what the skill is designed to do.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill references API keys, access credentials, and command execution but does not clearly warn users that it may touch sensitive secrets or perform executable actions. In the context of a supposedly benign interview skill, this omission is especially dangerous because users are less likely to expect or scrutinize privileged behavior.

Content

No source excerpt is available for this finding.