ClawHub
Back to skill

Security audit

card-full

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed credit-card research helper that searches public web sources and produces a structured report, with no hidden persistence or account-changing behavior found.

Before installing, understand that the skill will search the web for the card you ask about and may use your Brave API key if one is available. It is suitable for research reports, but users should independently verify current offers and terms before applying for any financial product.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 309)May include surrounding context.

md
### `## 🔗 Sources`
Numbered list of URLs fetched, as markdown hyperlinks with short "Site - Topic" labels.

## Output Rules

- Use one emoji per section heading.
- When listing credits, fees, or any monetary amounts, sort from highest to lowest dollar value.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The listed trigger phrases include "full report" and "tell me about the [card name]," and the activation condition says "when the user asks for a full credit card review, breakdown," which is broad natural language rather than a tightly scoped invocation. In a markdown skill description, this can overlap with ordinary conversation and there are no explicit negative examples or exclusion conditions to narrow when the skill should not activate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

Optional Brave template:

bash
curl -sS "https://api.search.brave.com/res/v1/web/search?q=CARD+NAME+review+welcome+offer&count=10" \
  -H "X-Subscription-Token: $BRAVE_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 236)May include surrounding context.

Optional Brave template:

bash
curl -sS "https://api.search.brave.com/res/v1/web/search?q=CARD+NAME+review+welcome+offer&count=10" \
  -H "X-Subscription-Token: $BRAVE_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 249)May include surrounding context.

Optional Brave template:

bash
curl -sS "https://api.search.brave.com/res/v1/web/search?q=CARD+NAME+review+welcome+offer&count=10" \
  -H "X-Subscription-Token: $BRAVE_API_KEY"

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 · references/delta-reserve-2026-offer-staleness.md (reported line 23)May include surrounding context.

md
stale tiers (70k, 100k@$5k). A structure-keyword query
   (`round-trip flight certificates`) surfaced the DoC page updated that same day.

2. **Trusted a "current" label without checking expiry.** TPG's tracker said "June 2026
   to now," but the Delta newsroom press release showed that structure was a limited-time
   offer expiring 7/15/26. No valid-through check was done.

Static analysis

No suspicious patterns detected.