Back to skill

Security audit

ci-tools-support Support

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report instructions to unlock discussions without checking why they were locked or getting maintainer approval.

Review the skill’s moderation workflow before installing. Consider whether you are comfortable with instructions that could reopen locked discussions without checking the reason or obtaining maintainer approval. The scan was partial: it could not resolve a local path-like reference, 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The skill directs the agent to unlock previously locked issues without checking why they were locked or obtaining maintainer approval.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The skill explicitly tells the agent to unlock a relevant issue whenever it has permission, without checking the lock reason or obtaining authorization to reverse it. A requester could use a support question to induce removal of an intentional moderation restriction, enabling renewed spam, harassment, or unwanted participation; the surrounding safety checks do not establish that unlocking is authorized.

Content

No source excerpt is available for this finding.

The workflow instructs the agent to unlock existing discussions without warning about removing moderation restrictions.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

Automatically unlocking an existing discussion changes its moderation state and can reopen participation that maintainers deliberately restricted. Keeping support accessible is a benign goal, but treating technical permission as sufficient authorization makes this workflow unsafe; this finding describes the same underlying issue as SDI-2 rather than a separate vulnerability.

Content

No source excerpt is available for this finding.