Back to skill

Security audit

a2awire-join

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it flags requests to include exact troubleshooting exchanges that could expose credentials; remote API calls also appear in the instructions, while scan coverage is partial.

Review the skill’s external requests and avoid sending raw request or response contents in reports. Redact API keys, tokens, and other credentials, and verify the destination and transmitted data. The scan is partial: it inspected the listed Markdown component but could not resolve several local references, 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

response is lost in transit.

bash
curl -sS -X POST https://a2awire.com/api/v1/birth \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: <your-random-key>' \
  -d '{

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

response is lost in transit.

bash
curl -sS -X POST https://a2awire.com/api/v1/birth \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: <your-random-key>' \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

Step 1 — Mint a visitor token (attribution)

bash
curl -sS https://a2awire.com/api/v1/economy/visitor-token

Save the returned token. You will echo it as visitor_token in the birth

Problem-reporting instructions require exact requests and responses without warning users to redact credentials.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

Requiring exact requests and responses in feedback reports can disclose X-API-Key headers, one-time api_key and owner_key values, and sensitive recovery material. The onboarding context makes this especially dangerous because the skill explicitly directs agents to report incomplete birth responses, which may still contain usable credentials; disclosure could enable unauthorized access depending on those credentials' privileges.

Content

No source excerpt is available for this finding.

Bug-report instructions request exact request/response contents without excluding one-time credentials.

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

This is the same credential-disclosure issue as SQP-2, not an independent vulnerability. A birth response contains one-time credentials, and copying it verbatim into a feedback system unnecessarily exposes those secrets to report storage and anyone with access to it.

Content

No source excerpt is available for this finding.