Intelica — Competitive Intelligence

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:06 AM UTC
• Version: 4.5.2

Overview

This is a disclosed third-party competitive-intelligence API skill whose main risks are sharing public company context and possible paid calls, with no hidden code or persistence found.

Install only if you are comfortable sending public company or market information to Intelica's API. Do not use it with confidential plans, regulated data, PII, or internal strategy, and set explicit budget limits before enabling payment-enabled autonomous use.

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

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

Findings (8)

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 96% confidence

Finding

This skill explicitly instructs the agent to send company names, URLs, descriptions, and context to a third-party API. Even though the document warns against submitting confidential or regulated data, the mechanism still creates a real data exfiltration path if an agent is mis-scoped, misconfigured, or given sensitive input by mistake.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

Step 0 — Get free trial key (no wallet needed)

text

GET https://api.intelica.dev/api-keys/trial
→ {"key": "ikey_trial_...", "calls_remaining": 5, "expires_at": "..."}

# Use immediately — extract response.key and pass as X-API-KEY header

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 96% confidence

Finding

The demo endpoint transmits user-supplied analysis text to api.intelica.dev without authentication, which lowers friction for accidental disclosure. The skill context says to use only public data, but the endpoint still externalizes whatever text the agent passes, making unintended leakage plausible.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Step 1 — Free demo (no payment, no key)

text

POST https://api.intelica.dev/demo
Content-Type: application/json

{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 97% confidence

Finding

The full analysis flow with trial key sends potentially rich company descriptions and context to an external service and introduces credential handling via X-API-KEY. This creates both a data-sharing risk and an operational risk if trial keys are logged, reused insecurely, or embedded in agent traces.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

Step 2 — Full analysis with trial key

text

POST https://api.intelica.dev/intel
X-API-KEY: ikey_trial_...
Content-Type: application/json

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 98% confidence

Finding

This endpoint combines third-party data transmission with autonomous paid execution via x402, increasing both privacy and financial risk. An agent could submit sensitive strategic context and also trigger chargeable requests if payment is configured, making misuse more damaging than a normal external API call.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

Step 3 — Full analysis with x402 payment

text

POST https://api.intelica.dev/intel
Content-Type: application/json

{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 97% confidence

Finding

The batch endpoint enables multiple third-party transmissions in one action, amplifying the blast radius of any mistake by allowing up to 10 analyses per request. If sensitive or internal targets are included, the skill can exfiltrate more data at once while also incurring automated cost.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

Step 4 — Batch (up to 10 analyses for $0.20)

text

POST https://api.intelica.dev/batch
X-PAYMENT: <x402 signed payment>
Content-Type: application/json

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 181)May include surrounding context.

md

- Networks: Base mainnet + Solana mainnet
- Standard: $0.05 USDC / Elite: $1.00 USDC / Batch: $0.20 USDC
- Trial: GET /api-keys/trial — 5 free calls, no wallet required
- x402 manifest: https://api.intelica.dev/.well-known/x402.json

## Links

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 186)May include surrounding context.

md

- Networks: Base mainnet + Solana mainnet
- Standard: $0.05 USDC / Elite: $1.00 USDC / Batch: $0.20 USDC
- Trial: GET /api-keys/trial — 5 free calls, no wallet required
- x402 manifest: https://api.intelica.dev/.well-known/x402.json

## Links

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 187)May include surrounding context.

md

- Networks: Base mainnet + Solana mainnet
- Standard: $0.05 USDC / Elite: $1.00 USDC / Batch: $0.20 USDC
- Trial: GET /api-keys/trial — 5 free calls, no wallet required
- x402 manifest: https://api.intelica.dev/.well-known/x402.json

## Links

Static analysis

No suspicious patterns detected.