Back to skill

Security audit

Fibek Cleo

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with a collections platform, but it handles credentials, long-lived tokens, and outbound debtor communications with under-specified safeguards.

Install only in an environment where FIBEK_BASE_URL is pinned to the legitimate HTTPS Fibek API and network egress is restricted. Treat the skill as handling sensitive financial and contact data; require users to review recipients, channels, and campaign audiences before any message or campaign is sent, and ensure bearer tokens are stored and cleared securely.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:10
Finding

Credentials and Long-Lived Bearer Tokens Are Sent to an Unrestricted API Origin

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:113
Finding

Swagger Discovery Permits Arbitrary Server-Side URL Requests

Content
View full analysis
Remediation
View remediation
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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instructions mandate a Spanish greeting and conversation flow, and later formatting rules also require Spanish status/date rendering. There is no opt-in or documented justification that this skill is intentionally limited to Spanish-speaking users, which creates a language-policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables sending payment reminders and account statements over external channels like email and WhatsApp without requiring an explicit user confirmation or warning about outbound disclosure. In a collections context, this can lead to unintended transmission of sensitive financial information to the wrong recipient or via an unintended channel, especially when contact selection is optional or ambiguous.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documented campaign validation and execution flows describe outbound campaign capabilities without any warning, approval gate, audience preview, or rate/impact constraints. In this business collections setting, a mistaken or overly broad execution could trigger mass debtor communications, causing privacy issues, reputational harm, and potentially unauthorized bulk outreach.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

These instructions require Spanish translations and Spanish-formatted dates/status text for all responses, indicating a fixed locale. Without a user language choice or a documented locale-specific justification, this is a natural-language policy violation.

Content

No source excerpt is available for this finding.