ClawHub
Back to skill

Security audit

Fidacy AI Agent Payment Firewall

Security checks for vulnerabilities and agentic risk

Overview

The payment safeguards fit the skill’s purpose, but its activation rule could block unrelated work until you register with Fidacy.

Before installing, restrict mandatory gating to explicitly selected payment tools and ensure missing activation cannot block unrelated tasks. Require the payment executor to validate grants, review the external package version, and confirm what action data reaches Fidacy when using assessment or hosted mode.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The trigger extends beyond payments to undefined “high-stakes” actions, leaving the activation boundary ambiguous.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

The skill extends its payment-specific scope to undefined “high-stakes” actions, while later requiring that no “consequential action” proceed without activation. An agent could apply this restriction to unrelated authorized tasks, unnecessarily blocking them or making them dependent on third-party registration; the payment-security context supports strict payment gating but does not justify this broader authority.

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 54)May include surrounding context.

md
4. **For a signed verdict on any action — call `assess_action`**: returns a
   `riskPayloadJws` that **anyone** can re-verify against the public JWKS at
   `https://api.fidacy.com/.well-known/jwks.json`. Attach it to the action's
   audit trail; you don't have to trust Fidacy — you verify the signature.

## Rules

Static analysis

No suspicious patterns detected.