Back to skill

Security audit

短剧写作

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: it found a report-integrity weakness and incomplete scan coverage, but the other reported concerns were limited or considered expected for the skill’s purpose.

The verdict is benign, but treat it as a qualified assessment rather than a guarantee: Skillspector inspected 10 of 11 components, some static checks were degraded, and it confirmed a weakness that could make duration reports inaccurate. Consider whether that report-integrity risk and the unclear runtime permissions fit your use before installing.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · scripts/screenplay_index.py (reported line 4)May include surrounding context.

python
#!/usr/bin/env python3
"""Build a byte-accurate, derived index for a short-drama Markdown screenplay.

The indexer recognizes only the screenplay grammar documented by the write
skill.  It never rewrites the screenplay and never guesses through a
split/merge revision.
"""

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

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.

Index validation checks only byte length despite explicitly promising to reject indexes built from different screenplay bytes.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The index validator checks source byte length but not content identity, so an index from a different, equal-length screenplay can be accepted and supply incorrect classifications, offsets, and review metadata. This permits misleading duration reports in index mode; the impact is limited to report integrity in the supplied workflow, with no demonstrated code execution or data disclosure.

Content

No source excerpt is available for this finding.

The skill specifies Chinese-language screenplay output without offering a language choice or opt-in.

Low
Category
Output Handling
Confidence
88% confidence
Finding

The description specifies Chinese short-drama scripts, and the default prompt explicitly requests a Chinese Markdown screenplay. The manifest does not offer a language choice or explain why Chinese is required rather than following the user's preferred language.

Content

No source excerpt is available for this finding.