ClawHub
Back to skill

Security audit

doc-updates

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-maintenance skill with broad repository checks and optional approved cleanup, but no hidden exfiltration, persistence, or deceptive behavior was found.

Install this only if you want an agent to help maintain repository documentation. Review the file list before approving consolidation, especially any delete or git staging step, and avoid running it for generic writing tasks outside a codebase.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
- [When to Use](#when-to-use)
- [Required TodoWrite Items](#required-todowrite-items)
- [Step 1: Collect Context](#step-1-collect-context-context-collected)
- [Step 2: Identify Targets](#step-2-identify-targets-targets-identified)
- [Step 2.5: Check for Consolidation](#step-25-check-for-consolidation-consolidation-checked)
- [Step 3: Apply Edits](#step-3-apply-edits-edits-applied)

Context Leakage

High
Category
Data Exfiltration
Confidence
78% confidence
Finding

The skill explicitly tells the agent to collect context from a prior workspace-review skill and use its notes to understand the delta. Because the skill is triggered by broad documentation-related terms, this can propagate and reuse repository-wide context that may exceed what is necessary for the current task, increasing the risk of oversharing sensitive codebase details into documentation workflows, follow-on tools, or user-visible output.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
9. `doc-updates:accuracy-verified`
10. `doc-updates:preview`

## Step 1: Collect Context (`context-collected`)

- Validate `Skill(sanctum:git-workspace-review)` has been run.
- Use its notes to understand the delta.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 280)May include surrounding context.

md
echo "Skills: $(find plugins/*/skills -name 'SKILL.md' | wc -l)"

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list contains broad, common terms such as "documentation," "writing," and "adr," which can cause this skill to activate in contexts far beyond its intended scope. That increases the chance of unintended execution of a workflow that reads repository context, inspects many files, and suggests shell commands, potentially exposing unrelated workspace data or causing confusing autonomous behavior.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · modules/accuracy-scanning.md (reported line 76)May include surrounding context.

md
Verifies that referenced paths exist.

**Patterns to detect:**
- Backtick paths: `` `plugins/sanctum/skills/doc-updates/SKILL.md` ``
- Relative paths in links: `[link](./modules/foo.md)`
- Configuration examples with paths

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation promises a read-only sync check with meaningful exit codes, but the shown script only prints discrepancies and never exits nonzero when drift is detected. In CI or automated quality gates, this can cause documentation integrity checks to silently pass even when capabilities are undocumented or stale, weakening release controls and enabling inaccurate or misleading docs to ship.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This module explicitly instructs destructive actions such as rm <file> and git add -u after only lightweight verification, but it does not clearly and prominently warn that approving recommendations will delete user files and stage those deletions in git. In an agent skill context, that creates a real risk of unintended data loss or silent repository modification, especially because the workflow presents deletions as routine cleanup steps within an automated documentation process.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.