ClawHub
Back to skill

Security audit

AgentFin

Security checks for vulnerabilities and agentic risk

Overview

This skill is transparent about using a payment-card API, but it gives agents direct access to card secrets, OTP codes, and fund-moving actions without strong approval or data-handling boundaries.

Install only if you intend to let the agent interact with AgentFin payment cards. Treat the API key, card details, and OTPs like payment credentials: require explicit approval before any credential lookup, top-up, purchase, or OTP use, and avoid logging or storing returned secrets.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly enables retrieval of full card credentials and 3DS OTP codes, which are highly sensitive payment secrets that can directly authorize transactions. Presenting these capabilities without strong warnings, consent requirements, or data-handling restrictions materially increases the risk of unauthorized purchases, credential exposure, and abuse by downstream agents or prompts.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 28)May include surrounding context.

Check Balance & Card Status

bash
curl -H "Authorization: Bearer $AGENTFIN_API_KEY" \
  https://agentfin.tech/api/me

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill provides operational instructions to top up cards and complete purchases but does not warn that these actions move funds and can create irreversible or hard-to-recover financial consequences. In an agent setting, this omission is dangerous because an agent may autonomously execute spending steps without clear approval boundaries or transaction safety checks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.