ClawHub
Back to skill

Security audit

tech-content-review-panel

Security checks for vulnerabilities and agentic risk

Overview

This article-review skill stays within its stated purpose, with practical cautions about searching unpublished wording and applying edits.

Use drafts whose wording you are comfortable sending to a search provider, or require approval of search queries for confidential material. Specify whether you want recommendations only or authorized edits, and keep a copy before revisions.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Mandatory originality searches can disclose unpublished draft content without a privacy warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The mandatory originality check sends core arguments, frameworks, and distinctive wording to an external search service without requiring a confidentiality check or user approval. Because this skill specifically reviews unpublished drafts, those queries could disclose proprietary research, confidential claims, or identifying passages even without uploading the complete article.

Content

No source excerpt is available for this finding.

The workflow instructs the agent to apply article revisions despite the manifest explicitly limiting the skill to review and advisory revision guidance.

Medium
Category
Excessive Agency
Confidence
92% confidence
Finding

The manifest limits this skill to review and advisory revision guidance, but the workflow subsequently directs the agent to apply fixes. This creates an authorization ambiguity that could turn a review request into unsolicited rewriting; modifying the source file would additionally depend on available tools and how the agent interprets these instructions.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: description clause 'Trigger when the user asks to 会审/评审/review a finished deep-analysis draft or wants tech content 接近完美/可发布' activates on 'to', which is too short and may match unintended inputs

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% 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.

Content

Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.

md
use direct statements or two complete sentences; preserve a natural contrast when it carries the judgment.
5. **Professional-vs-distribution tension is not forced into agreement** — list options for the author to decide. Principle: a hook must not sacrifice professional credibility, but must not be so professional that no one clicks.
6. **Reader-fit feedback cannot override the positioning lock** — the reading test diagnoses misunderstanding; it does not grant every role editorial authority to expand scope, change genre, add unsupported material or flatten technical depth.
7. **Do not average roles or chase unanimity** — fix factual/technical misreadings even if one role reports them; adopt comprehension fixes only when compatible with the intended reading task; park preference conflicts explicitly.
8. **Scope and length are quality constraints** — do not add examples, tables, definitions or sections merely because a reader requested them. Every addition must repair a named comprehens