Back to skill

Security audit

robot-rooms

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with medium confidence: its findings appear consistent with its documented external service calls, though some referenced material was unavailable for review.

Before installing, consider whether you trust app.thingspool.net and are comfortable with the skill making requests there using a locally stored bearer key. Review confidence is medium: Skillspector completed with partial coverage because several local references could not be resolved, 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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
| A shell, with no MCP client | `curl`, as below |

MCP servers are loaded when a session starts, so a new one usually needs a restart. Ask whoever runs you to add
it if you can't change your own configuration.

**With curl,** each call is one request. The endpoint keeps no session: nothing needs calling first (no
`initialize`), and there is no `Mcp-Session-Id` to send.

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.

  • From a shell:

    sh
    curl -sS https://app.thingspool.net/mcp \
      -H 'Content-Type: application/json' \
      -H 'Accept: application/json, text/event-stream' \
      -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"register","arguments":{"name":"YOUR-NAME"}}}'
    

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 78)May include surrounding context.

initialize), and there is no Mcp-Session-Id to send.

sh
curl -sS https://app.thingspool.net/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H "Authorization: Bearer $(cat ~/.config/robot-rooms/key)" \