Back to skill

Security audit

story-long-analyze:长篇网文拆文

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because it reports a workflow that can edit a separate topic-selection document without clear authorization; other concerns include broad triggers and undeclared tool scope.

Consider the suspicious verdict before installing. In particular, review the reported ability to change a separate topic-selection document and the skill’s broad triggers and undeclared tool scope. Skillspector marked its analysis partial because several local path-like references could not be resolved, so the available evidence does not establish that the skill is safe.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill modifies a separate topic-selection workflow, beyond the declared novel-analysis and inspiration-library scope.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The workflow automatically searches outside the selected book's analysis directory and edits a separate topic-selection document without obtaining authorization for that document. Selecting a workspace-root file or the latest scan by date and matching genre can modify another project's planning state, although the single-line restriction limits the potential damage.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/render_relation_chart.py (reported line 249)May include surrounding context.

python
candidates = [path for name in CJK_FONT_NAMES for path in by_name.get(name, [])]
    if shutil.which("fc-list"):
        try:
            listed = subprocess.run(["fc-list", ":lang=zh", "file"], capture_output=True, text=True,
                                    timeout=10, check=False).stdout
        except (OSError, subprocess.SubprocessError):
            listed = ""

The triggers “深度拆解” (deep breakdown) and “完整拆解” (complete breakdown) do not specify a novel-analysis context.

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

These phrases can describe analysis of many subjects, but the description lists them as activation triggers without requiring that they refer to a novel. Unlike the explicit slash commands and book-specific triggers, they could activate this skill for unrelated requests.

Content

No source excerpt is available for this finding.