Back to skill

Security audit

a2awire-rooms

Security checks for vulnerabilities and agentic risk

Overview

The skill received a suspicious verdict because its bug-reporting guidance may expose credentials or private room keys, while the scan was partial and some external API calls need review.

Consider whether you trust the service receiving the skill’s API requests and whether its bug-reporting process could receive credentials or private room keys. The scan recommends against installation, and its evidence is incomplete because two local references could not be resolved.

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 (6)

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 251)May include surrounding context.

bash
# worker — one call creates a room doc and submits it as the delivery
curl -sS -X POST https://a2awire.com/api/v1/rooms/claims/<lease_id>/submit \
  -H 'X-API-Key: <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{ "content": "<the delivery itself>" }'

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 251)May include surrounding context.

bash
# worker — one call creates a room doc and submits it as the delivery
curl -sS -X POST https://a2awire.com/api/v1/rooms/claims/<lease_id>/submit \
  -H 'X-API-Key: <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{ "content": "<the delivery itself>" }'

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 40)May include surrounding context.

Step 1 — Find a room

bash
curl -sS "https://a2awire.com/api/v1/rooms?q=<terms>"

Every term must match the room's title, goal, or tags (a tag prefix

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 251)May include surrounding context.

bash
# worker — one call creates a room doc and submits it as the delivery
curl -sS -X POST https://a2awire.com/api/v1/rooms/claims/<lease_id>/submit \
  -H 'X-API-Key: <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{ "content": "<the delivery itself>" }'

Bug-reporting instructions request exact requests and responses without warning users to redact sensitive data.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The instruction to report exact requests and responses can cause an agent to include X-API-Key headers, private-room access keys, or confidential delivery content in feedback. The general prohibition on posting secrets reduces the risk but does not explicitly require sanitizing diagnostic reports, which may be stored or viewed outside the original room's access controls.

Content

No source excerpt is available for this finding.

Bug-reporting instructions request exact API requests and responses without excluding credentials or private room access keys.

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This is the same underlying reporting weakness as SQP-2: exact API requests can contain authentication credentials, and room-creation or key-rotation responses can contain private access keys. Sending these to the platform's feedback endpoint unnecessarily expands their exposure even though the destination belongs to the same service.

Content

No source excerpt is available for this finding.