ClawHub
Back to skill

Security audit

InvestLog AI

Security checks for vulnerabilities and agentic risk

Overview

This stock-research skill is limited and mostly transparent, but it asks users to put an API key in URL requests, which can expose that key in logs or histories.

Review this skill before installing if you plan to use a paid API key. Avoid including private portfolio details, account data, personal identifiers, or secrets in stock questions, because the query is sent to InvestLog. Do not place a valuable API key in a URL unless you accept the logging risk; prefer a version of the skill or API that supports an Authorization header, and rotate any key that may have been exposed in query strings.

A.I.G

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

Warning
Location
SKILL.md:103
Finding

API Credential Transmitted in a URL Query Parameter

Content
View full analysis
`. 3. The complete request URL is retained by the agent platform, a proxy, the API service, or monitoring infrastructure. 4. An attacker or unauthorized operator with access to those records extracts the API key. 5. The attacker submits requests using the exposed key until it is revoked or expires. ### Impact Assessment An exposed credential could enable unauthorized use of the victim's InvestLog account, including consumption of paid query quotas and possible account-related charges. The access obtained is limited to the privileges granted to the compromised API key; the reviewed file provides no evidence that the key grants local system ...[truncated 65 chars]
Remediation
View remediation
``` 2. Update the API and Skill documentation so API keys are never embedded in URLs. 3. Ensure the agent platform, proxy, and API service redact authentication headers from logs and diagnostic output. 4. Avoid displaying credentials in tool-call transcripts or generated responses. 5. Rotate any API keys that may already have been used in query parameters. 6. Apply expiration, quota limits, and revocation controls to issued credentials. ]]>

other

Note
Location
SKILL.md:47
Finding

Unrestricted Forwarding of User-Supplied Text to a Third-Party API

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

md
- **API key**: After free trial, register at https://api.investlog.ai to get your API key and pass it as a query parameter: `&api_key=il_your_key`
- **Plans**: Basic ($9.9/mo, 100 queries/day) | Pro ($19.9/mo, 300 queries/day)

## Output guidelines

- Present data in a clear, readable format
- For list data (holdings, transactions), use tables when possible

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 17)May include surrounding context.

Basic query

text
web_fetch url="https://api.investlog.ai/api/v1/query?query=Is+NVDA+overvalued" extractMode=text

Query with specific skill and symbol

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 25)May include surrounding context.

Basic query

text
web_fetch url="https://api.investlog.ai/api/v1/query?query=Is+NVDA+overvalued" extractMode=text

Query with specific skill and symbol

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 34)May include surrounding context.

Basic query

text
web_fetch url="https://api.investlog.ai/api/v1/query?query=Is+NVDA+overvalued" extractMode=text

Query with specific skill and symbol

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 37)May include surrounding context.

Basic query

text
web_fetch url="https://api.investlog.ai/api/v1/query?query=Is+NVDA+overvalued" extractMode=text

Query with specific skill and symbol

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 40)May include surrounding context.

Basic query

text
web_fetch url="https://api.investlog.ai/api/v1/query?query=Is+NVDA+overvalued" extractMode=text

Query with specific skill and symbol

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs users to place the API key in the URL query string (&api_key=...). Query parameters are commonly logged by clients, proxies, browser history, observability systems, and upstream servers, which can expose credentials beyond their intended scope. Because this skill is designed around repeated external web requests, the leakage risk is realistic rather than theoretical.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.