Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
Overview
This Instagram content skill is a local writing aid with clearly disclosed optional local draft saving and no evidence of account access, automation, exfiltration, or destructive behavior.
Installers should understand that saved captions are stored locally in the OpenClaw workspace memory directory. Use chat-only rewrites if you do not want draft content persisted, and consider narrowing triggers if your environment auto-routes skills aggressively.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This manifest file defines "fix my carousel" as a trigger, but that phrase is generic enough to appear in ordinary discussion without clearly indicating invocation of this specific skill. The manifest does not include narrowing context, exclusions, or negative examples to distinguish when the skill should activate versus when it should not.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The example triggers are generic natural-language requests such as rewriting hooks, fixing captions, or making posts less boring. In systems that auto-route skills based on example phrases, overly broad triggers can cause this skill to activate unintentionally for ordinary writing or marketing requests, leading to misrouting and unexpected access to local draft-writing behavior. The skill’s local-first and no-automation scope reduces severity, but the broad matching remains a genuine invocation-safety issue.
- Content
Static analysis
No suspicious patterns detected.