Back to skill

Security audit

Repo2

Security checks for vulnerabilities and agentic risk

Overview

This self-evolution skill has a coherent purpose, but it grants broad autonomous code-changing, external Hub, auto-update, and rollback powers with insufficient scoping and disclosure.

Install only in a disposable repository or controlled test environment. Disable bridge execution, Hub connectivity, auto-publish, and auto-update unless you explicitly want them; use review or dry-run mode; require a clean Git worktree before running; and avoid exposing private session logs, memory files, credentials, or business-sensitive code to this skill.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (4)

T01 · Skill Instruction Hijacking

Error
Location
src/gep/prompt.js:5
Finding

Untrusted Hub content is injected into an autonomous code-editing agent

Content
View full analysis
0) { payload.questions = o.questions; } const msg = { protocol: 'gep-a2a', protocol_version: '1.0.0', message_type: 'fetch', message_id: `msg_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`, sender_id: nodeId, timestamp: new Date().toISOString(), payload, }; const url = `${HUB_URL.replace(/\/+$/, '')}/a2a/fetch`; const controller = new AbortController(); const timer = setTimeout(() => controller.abort(), 8000); const res = await fetch(url, { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify(msg), signal: controller.signal, }); clearTimeout(timer); if (!res.ok) return { tasks: [] }; const data = await res.json(); const respPayload = data.payload || data; const tasks = Array.isArray(respPayload.tasks) ? respPayload.tasks : []; const result = { tasks }; ``` ```js // src/evolve.js const fetchResult = await fetchTasks({ questions: proactiveQuestions }); const hubTasks = fetchResult.tasks || []; if (hubTasks.length > 0) { const best = selectBestTask(hubTasks); if (best) { const alreadyClaimed = best.status === 'claimed'; co ...[truncated 4731 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
src/gep/questionGenerator.js:96
Finding

User conversation fragments are transmitted to an external Hub without sanitization or explicit consent

Content
View full analysis
0) { var featureContext = featureLines[0] .replace(/\s+/g, ' ') .trim() .slice(0, 150); candidates.push({ question: 'User requested a feature that may benefit from community solutions: ' + featureContext + ' -- Are there existing implementations or best practices for this?', amount: 0, signals: ['user_feature_request', 'community_solut ...[truncated 2816 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
src/evolve.js:457
Finding

Routine maintenance force-updates executable Skills without version pinning or local integrity verification

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
src/gep/solidify.js:659
Finding

Failure rollback can erase unrelated tracked and staged user changes

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (177)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented purpose is a self-evolution engine, but the static findings indicate materially broader behaviors including transport messaging, asset exchange, process control, git mutation, packaging, and external publication. That mismatch is dangerous because operators may grant trust and run the skill under assumptions that do not match its real privileges or side effects.

Content

No source excerpt is available for this finding.