financialmodelingprep

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:57 AM UTC
• Version: 1.0.0

Overview

This is a non-executable guide for using the FMP financial-data API, with disclosed API-key handling, citation, quota, and investment-advice safeguards.

Install only if you intend the agent to use your FMP account for financial-data lookups. Keep FMP_API_KEY in the environment, expect FMP quota usage, and treat outputs as informational data that should be independently verified before financial decisions.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 80% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · tests/failure-cases.md (reported line 44)May include surrounding context.

md

---

## 5. Investment advice without disclaimer
**Bad:**
> "Tesla's DCF is below price, so it's overvalued — you should sell."

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 80% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · tests/skill-evaluation.md (reported line 43)May include surrounding context.

md

| Compliance | Gives advice, no disclaimer | Disclaimer missing in places | Disclaimer present, no recommendation |

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 · prompts/symbol-resolution.md (reported line 36)May include surrounding context.

md

> User: "Get Apple's revenue."
> Agent immediately calls `/income-statement?symbol=APPL` (typo) → empty array, or
> calls `/income-statement?symbol=AAPL` without confirming and happens to pull a
> different cross-listed entity. No confirmation, no profile check.

## Good
> User: "Get Apple's revenue."

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 · tests/failure-cases.md (reported line 94)May include surrounding context.

md

## 10. Guessing the ticker
**Bad:**
> User: "Get Delta's numbers." Agent pulls `DAL` without asking, but the user meant a
> different "Delta" company.

**Corrected:**

Static analysis

No suspicious patterns detected.