ClawHub
Back to skill

Security audit

Interactive Doc Mapper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local workflow-documentation generator with no evidence of hidden network access, persistence, or credential handling.

Install only if you are comfortable letting the agent inspect the target repository and write the chosen JSON, validation, and HTML output files. Keep generated files in the workspace and avoid putting secrets, customer data, cookies, tokens, or private URLs into the flow JSON because that content is embedded into the HTML output.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Ae1

High
Category
analysis-evasion
Content
- `scripts/generate_interactive_doc.py`
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to read repository contents, create or update JSON artifacts, and generate HTML output, which implies file read/write behavior, but it does not declare any explicit tool scope or permissions boundaries. This can lead to over-broad agent execution where the runtime may permit unintended filesystem access beyond the files needed for documentation generation, increasing the risk of unauthorized reads, overwrites, or leakage into generated artifacts.

Session Persistence

Medium
Category
Rogue Agent
Content
pill.textContent = `${label}: ${value}`;
        meta.append(pill);
      });
      const stepList = document.createElement("ol");
      stepList.className = "step-list";
      stepList.dataset.stepList = action.id;
      (action.steps || []).forEach((step, index) => {
Confidence
75% 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.

Session Persistence

Medium
Category
Rogue Agent
Content
pill.textContent = `${label}: ${value}`;
        meta.append(pill);
      });
      const stepList = document.createElement("ol");
      stepList.className = "step-list";
      stepList.dataset.stepList = action.id;
      (action.steps || []).forEach((step, index) => {
Confidence
75% 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.

Session Persistence

Medium
Category
Rogue Agent
Content
pill.textContent = `${label}: ${value}`;
        meta.append(pill);
      });
      const stepList = document.createElement("ol");
      stepList.className = "step-list";
      stepList.dataset.stepList = action.id;
      (action.steps || []).forEach((step, index) => {
Confidence
75% 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.

Session Persistence

Medium
Category
Rogue Agent
Content
pill.textContent = `${label}: ${value}`;
        meta.append(pill);
      });
      const stepList = document.createElement("ol");
      stepList.className = "step-list";
      stepList.dataset.stepList = action.id;
      (action.steps || []).forEach((step, index) => {
Confidence
75% 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.

Session Persistence

Medium
Category
Rogue Agent
Content
pill.textContent = `${label}: ${value}`;
        meta.append(pill);
      });
      const stepList = document.createElement("ol");
      stepList.className = "step-list";
      stepList.dataset.stepList = action.id;
      (action.steps || []).forEach((step, index) => {
Confidence
75% 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.

Tainted flow: 'report' from pathlib.Path.read_text (line 749, file read) → pathlib.Path.write_text (file write)

Medium
Category
Data Flow
Content
if args.validation_out:
            validation_path = Path(args.validation_out)
            validation_path.parent.mkdir(parents=True, exist_ok=True)
            validation_path.write_text(json.dumps(report, indent=2, sort_keys=True), encoding="utf-8")
        if not report["ok"]:
            raise FlowDocError("Flow document is invalid:\n- " + "\n- ".join(report["errors"]))
        out = write_html(data, args.out)
Confidence
65% confidence
Finding
Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Scope Creep

Low
Category
Excessive Agency
Content
and to permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The rendered document sets `<html lang="en">`, which forces an English locale in the generated output. This file does not indicate that the skill is region-specific or that users can choose the language, so it creates a minor natural-language policy concern.

Static analysis

No suspicious patterns detected.