Back to skill

Security audit

Financial Times Deep Reader

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for reading and summarizing Financial Times articles, but it needs review because it directs agents to use stored FT credentials and a persistent browser profile automatically.

Before installing, confirm you want agents to access FT.com with a stored account and persistent browser session. Prefer a dedicated FT-only browser profile, avoid placing real passwords in the skill text, and require explicit user approval before each authenticated run.

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
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description and capabilities specify bilingual analysis and English-Chinese summaries as a fixed behavior. This is a natural-language locale policy issue because it forces a specific language pair without offering the user a choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to log into FT.com using stored credentials and a persistent browser profile, but it provides no user-facing warning, consent boundary, or limitation on when account access is appropriate. In an agent setting, this can cause unintended use of a paid or personal account, expose subscription-backed content handling risks, and normalize silent account actions without clear authorization.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The constraints section explicitly says to always provide both English and Chinese translations, which removes user language choice. This violates the language/locale policy criteria because the skill mandates a specific bilingual format rather than offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.