ClawHub
Back to skill

Security audit

Ontology Mapper

Security checks for vulnerabilities and agentic risk

Overview

This skill provides construction ontology-mapping guidance and sample Python code without hidden execution, exfiltration, persistence, or privilege-escalation behavior.

Installers should be aware that the skill may read user-specified local project files and produce exports, so provide only construction data files intended for mapping. The inspected artifacts do not show hidden network use, destructive actions, credential access, or persistence.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 207)May include surrounding context.

md
SemanticMapping("IfcWindow", OntologyType.IFC, "08",
                OntologyType.MASTERFORMAT, RelationType.BROADER, MappingConfidence.MEDIUM),
        ]
        return rules

    def _build_synonym_map(self) -> Dict[str, List[str]]:
        """Build synonym mappings for fuzzy matching"""

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L013 includes a Russian-language book title together with an English translation, but the document does not explain whether the skill expects or prefers a specific language context. This can create avoidable language/locale ambiguity in user-facing documentation without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.