ClawHub
Back to skill

Security audit

Diagram Generator

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: its checks found no AIG issues, while the reviewed Skillspector flags were judged consistent with a diagram-generation skill; some analysis was incomplete.

The verdict is benign, but confidence is medium and the scan is partial: 35 of 36 components were fully inspected, one script was only partly interpreted, and five PNG files were outside the analyzer's supported scope. Consider that coverage limitation before installing.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

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 · AGENTS.md (reported line 44)May include surrounding context.

md
7. Replace every placeholder with concrete content from the brief or a clearly labeled assumption.
8. Run the final audit checklist from `resources/generation-rules.md` before returning the file.

## Output Rules

- Return only the final HTML when the user asks for a file body.
- If writing to disk is available, create a meaningful filename such as `system-map.html`.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.en.md (reported line 121)May include surrounding context.

bash
mkdir -p ~/.claude/skills
ln -s /absolute/path/to/diagram-generator ~/.claude/skills/diagram-generator

Then ask:

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 121)May include surrounding context.

bash
mkdir -p ~/.claude/skills
ln -s /absolute/path/to/diagram-generator ~/.claude/skills/diagram-generator

然后这样提问：

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.en.md (reported line 138)May include surrounding context.

bash
mkdir -p ~/.codex/skills
ln -s /absolute/path/to/diagram-generator ~/.codex/skills/diagram-generator

Gemini

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 138)May include surrounding context.

bash
mkdir -p ~/.codex/skills
ln -s /absolute/path/to/diagram-generator ~/.codex/skills/diagram-generator

Gemini

L17 requires English visible text without offering a language choice or opt-in.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The requirement explicitly constrains the generated diagram's visible text to English. It provides neither user opt-in nor a documented justification for this language restriction.

Content

No source excerpt is available for this finding.