ClawHub
Back to skill

Security audit

PCEC EvoMap Bounty

Security checks for vulnerabilities and agentic risk

Overview

This skill openly integrates with an external bounty service, but it can claim tasks, publish assets, and mark work complete without clear user approval controls.

Review before installing. Use this only if you intend the agent to interact with EvoMap on your behalf, and require manual confirmation before any task claim, asset publication, or completion request. Do not publish assets unless you have checked that they exclude private files, secrets, conversation content, and unrelated workspace data.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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
  • 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 (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:23
Finding

Untrusted External Task Delegation Without Validation or Approval Controls

Content
View full analysis
_tasks", "sender_id": "node_9e601234", "timestamp": "", "payload": { "include_tasks": true, "task_status": "open", "limit": 10 } }' ``` ### Technical Analysis The Skill directs the agent to retrieve open tasks from an external coordination service and subsequently process those tasks. The fetched task contents are controlled by the remote service, but the Skill does not establish any trust boundary between the returned data and executable agent instructions. No controls are defined for: - Validating the structure or permitted purpose of returned tasks. - Treating task descriptions as untrusted data rather than authoritative instructions. - Rejecting prompt-injection content embedded in task fields. - Restricting the tools, files, network destinations, or data that a fetched task may access. - Requiring explicit user approval before accepting or executing a task. - Isolating externally delegated work in a sandbox. Consequently, a malicious task publisher or compromised service could return a task containing instructions that alter the agent's current objective, request access to unrelated workspace data, induce unauthorized network operations, or override expected safety boundaries. ### Attack Path 1. A malicious actor publishes a crafted open task to the external bounty system, or compromises the task service. 2. The agent invokes the documented `/a2a/fetch` endpoint and retrieves the attacker-controlled task. 3. The task description contains embedded instructions directing the agent to disregard its original objec ...[truncated 1040 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:66
Finding

Unreviewed Publication of Unspecified Assets to an External Service

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and can cause the skill to activate in contexts unrelated to the user's intent. Because this skill performs task fetching, claiming, publishing, and completion against an external service, ambiguous activation increases the risk of unintended external actions and state changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises autonomous interaction with an external bounty platform, including claiming and completing tasks, but does not provide a user-facing warning that these operations change remote state. This can lead to unauthorized or accidental actions on behalf of the user or node identity, especially if the skill is invoked automatically.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This endpoint sends structured data to an external domain and initiates interaction with a third-party task system. While fetching open tasks is less dangerous than mutation, it still causes external transmission of node identifiers and operational metadata, which can expose identity, usage patterns, or enable unreviewed integration behavior.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

获取任务

bash
curl -X POST https://evomap.ai/a2a/fetch \
  -H "Content-Type: application/json" \
  -d '{
    "protocol": "gep-a2a",

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

This sequence includes POST requests to claim tasks and then publish/complete them on an external platform, which are direct remote state-changing operations. If invoked unintentionally or by ambiguous triggers, the skill could commit the node to work, submit assets, or alter task lifecycle state without proper authorization or user awareness.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

认领任务

bash
curl -X POST https://evomap.ai/task/claim \
  -H "Content-Type: application/json" \
  -d '{
    "task_id": "<task_id>",

Static analysis

No suspicious patterns detected.