skill-collision-guard

• Outcome: Pass
• Latest audit: Sep 23, 2026 · 2:19 AM UTC
• Version: 0.1.1

Overview

This skill is a disclosed local helper for comparing coding-agent skills and does not show hidden installation, execution, exfiltration, or destructive behavior.

Install only if you want a local preflight tool for skill collisions. Be aware it can read SKILL.md files from known agent skill directories, clone Git references you provide for inspection, and store reversible session-suppression state locally.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md

- The detector reads `SKILL.md` text and metadata. It never executes code from a candidate and never installs, removes, renames, or edits an installed skill.

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md

- The detector reads `SKILL.md` text and metadata. It never executes code from a candidate and never installs, removes, renames, or edits an installed skill.

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md

- The detector reads `SKILL.md` text and metadata. It never executes code from a candidate and never installs, removes, renames, or edits an installed skill.

Lp1

High

• Category: MCP Least Privilege
• Confidence: 75% confidence

Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · src/analyzer.js (reported line 25)May include surrounding context.

js

['write policy', /\b(read[- ]only|do not (edit|implement|modify)|no code changes)\b/i,
    /\b(implement|edit files|make the change|write the code)\b/i],
  ['approval policy', /\b(ask|confirm|approval).{0,30}\b(before|first)\b/i,
    /\b(do not ask|without asking|proceed autonomously|no confirmation)\b/i],
  ['test policy', /\b(skip|do not (run|write)|without)\s+(the\s+)?tests?\b/i,
    /\b(test[- ]driven|run (the )?tests|write tests|red[- ]green[- ]refactor)\b/i],
];

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · src/analyzer.js (reported line 25)May include surrounding context.

js

['write policy', /\b(read[- ]only|do not (edit|implement|modify)|no code changes)\b/i,
    /\b(implement|edit files|make the change|write the code)\b/i],
  ['approval policy', /\b(ask|confirm|approval).{0,30}\b(before|first)\b/i,
    /\b(do not ask|without asking|proceed autonomously|no confirmation)\b/i],
  ['test policy', /\b(skip|do not (run|write)|without)\s+(the\s+)?tests?\b/i,
    /\b(test[- ]driven|run (the )?tests|write tests|red[- ]green[- ]refactor)\b/i],
];