ClawHub
Back to skill

Security audit

SMS Campaign Compliance

Security checks for vulnerabilities and agentic risk

Overview

The skill’s broken checks can report “No flags” for risky marketing texts, making its advertised safeguards unreliable.

Treat this as requiring review because its advertised safeguards do not work reliably, not because malicious behavior was found. Do not rely on “No flags” to approve a campaign. Have the matching logic and promised checks corrected and independently verified, while retaining human review. The optional Windows app is unnecessary for the local workflow and has not been assessed here.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The script is nominally aimed at SMS compliance, but its implementation does not deliver key declared functions. Although it imports re and defines regex rules, it uses pattern in low instead of regex matching. Normal phrases such as 'you won' therefore will not match the corresponding pattern. Its static guardrails caution against inventing consent records but do not explain which records must be retained or how opt-outs must be handled. Local input reading and report writing are ordinary supporting operations; no unrelated access or undeclared external activity is evident.

Content

No source excerpt is available for this finding.

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

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.

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 29)May include surrounding context.

md
## The job

A text goes out with a prize claim and no opt-out language, a subscriber complains, and the sender has no consent record to point at.

## What you get

The advertised risk checker compares regex definitions as literal text, causing ordinary risky drafts to receive 'No flags'.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker tests whether an entire regex definition appears literally in the draft rather than evaluating that regex, so ordinary phrases such as 'you won' or 'guaranteed approval' will not trigger their intended rules. In a pre-send compliance workflow, the resulting 'No flags' report can provide false reassurance and allow risky marketing messages through; the human-review disclaimer reduces but does not eliminate this risk.

Content

No source excerpt is available for this finding.

The generated report omits the promised consent-record and opt-out handling requirements.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The skill promises consent-record and opt-out handling requirements, but this report provides only generic guardrails, including a warning against inventing consent records. Users relying on it as the advertised pre-send checklist may overlook missing consent evidence or ineffective opt-out processing, creating compliance and unwanted-messaging risks; the script itself does not send messages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.