Back to skill

Security audit

openspace

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported excessive-agency flag was judged expected for the skill’s purpose, though the overall evidence is incomplete.

The scanners returned a benign verdict, but confidence is medium and Skillspector’s analysis was partial: it reported 0% complete coverage, with both listed components only partially inspected and tool-misuse analysis degraded. Consider this limitation before installing, especially if you need a more complete review.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
- Keep `task` concrete and goal-oriented.
- Use `skill_dirs` so OpenSpace can reuse/evolve host skills.
- Use `search_scope: "all"` unless you explicitly want local-only.
- Expect longer runtimes; do not chain OpenSpace calls back-to-back without checking results.
- If `openspace__execute_task` fails due to a broken skill, consider `openspace__fix_skill`.

## Result Handling