ClawHub
Back to skill

Security audit

DoctorClaw Feedback Digest

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed customer-feedback digest skill with expected data collection, delivery, and archiving behavior, but users should handle customer data carefully.

Install only if you are comfortable letting the agent read the feedback sources you configure, summarize customer content, send digests to chosen channels, and store dated digest archives. Use authorized sources, redact unnecessary personal details, and set your own retention rules for archived feedback.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to ingest customer feedback from reviews, surveys, tickets, and social mentions, which commonly contain personal data, sensitive complaints, and account-specific details. It also contemplates sending digests over external channels, but provides no user-facing warning or handling guidance about privacy, consent, redaction, retention, or transmission risk, creating a realistic chance of inappropriate collection or disclosure.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

md
- Apologize where appropriate
- Offer a solution or next step
- Match the configured response style
- Mark as DRAFT — never post without approval

### Step 5: Compile Digest

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The archive step instructs the agent to save digests to disk under a dated path, which creates persistent storage of customer-derived content and trend history. Because the skill gives no warning about retention, access control, or redaction, sensitive customer statements and identifiers could be unnecessarily retained and later exposed to other users, tools, or backups.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.