Back to skill

Security audit

troubleshooting-guide-writer

Security checks for vulnerabilities and agentic risk

Overview

The verdict is suspicious because scanners report that the skill’s script produces a brief-validation report instead of the troubleshooting guide its description promises; no malicious behavior was reported by the completed AIG scan.

Consider avoiding installation until the author clarifies the skill’s actual output and declared tool scope. The scanners report no malicious behavior, but some references were unresolved, so the evidence is incomplete.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The script reads fields related to troubleshooting guides, but its output contains only their validation status and static guardrails—not the supplied field contents or newly written guide content. Its implemented primary function is therefore materially narrower and different from the declared guide-writing purpose. Local file reading and writing support that function; no unrelated resource access or hidden external activity is evident.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% 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 · SKILL.md (reported line 30)May include surrounding context.

md
## The job

Experienced technicians fix faults from memory, so new hires call the senior tech for every problem, and the written steps that do exist skip the safety limits that caused a near miss.

## What you get

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.

The skill produces a brief-validation report rather than the troubleshooting guide promised by its manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a troubleshooting guide with ordered diagnostic steps, safety limits, and escalation triggers. At L99–L111, field contents are reduced to character counts or missing/overlength notices; L120–L123 then append generic guardrails and save the report as troubleshooting-guide.md. The output neither includes the supplied diagnostic and repair instructions nor generates the promised guide.

Content

No source excerpt is available for this finding.