ClawHub
Back to skill

Security audit

diagram-generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed diagram-generation integration that sends diagram prompts to its configured API and includes reasonable review, export, and privacy boundaries.

Install this only if you are comfortable sending diagram prompts and related structure to the configured AI Skills API and paying for successful operations. Protect the API key, avoid placing secrets in diagram prompts, and review the generated plan before rendering or sharing exported artifacts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

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 · references/HTTP-REQUESTS.md (reported line 9)May include surrounding context.

  • POST /api/v1/diagram-generation/diagram.render；GET /api/v1/diagram-generation/diagram.render/tasks/{task_id}
sh
curl -sS -X POST "$BASE/diagram-generation/diagram.plan" \
  -H "Authorization: Bearer $DIAGRAM_GENERATION_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_UUID" \

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s user-facing natural-language content is entirely Chinese, including the description and operational instructions. This can violate language/locale policy when the skill does not explicitly offer users a language choice or document that it is intentionally limited to Chinese-speaking users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file’s natural-language instructions are entirely Chinese and do not mention that the skill is Chinese-only, region-specific, or that users can choose another language. Under the stated policy, forcing a specific language without opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.