Back to skill

Security audit

bolo-jiimore

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Amazon market research API client, with ordinary integration risks around external queries and API-key handling but no artifact-backed malicious behavior.

Install only if you intend to send Amazon market-research keywords and filters to LinkFoxAgent. Avoid entering confidential product ideas unless you accept that external processing, store the API key in a proper secret manager or protected config instead of a general shell profile, do not print the full key in the terminal, and consider using a pinned dependency file in a virtual environment.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
README.md:270
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
references/API-Overview.md:28
Finding

API Key Disclosure Through Terminal Output and Plaintext Shell Configuration

Content
View full analysis
> ~/.bashrc source ~/.bashrc ``` ### Technical Analysis The verification command prints the complete API key to standard output. Terminal scrollback, shell-session recordings, support captures, CI logs, remote-session logging, or a nearby observer may retain or observe the credential. The persistent setup instructions also place the key in plaintext in a shell startup file. Any local account, backup process, diagnostic collector, or application able to read that file may recover the credential. Shell profiles may also be copied into backups or accidentally shared during troubleshooting. Reading the key from an environment variable and transmitting it as an HTTPS authorization header to the documented LinkFoxAgent endpoint is necessary for the declared API functionality. The weakness is specifically the documentation's disclosure and storage guidance, not the authenticated network request itself. ### Attack Path 1. A user configures `LINKFOXAGENT_API_KEY` and follows the documented verification command. 2. The complete key is printed to the terminal and may be retained in scrollback, recordings, logs, or screenshots. 3. Alternatively, the user stores the key in plaintext in a shell startup file as instructed. 4. An attacker or unauthorized local process gains access to the terminal output, recording, b ...[truncated 618 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (16)

YARA rule 'backdoor_persistence': Backdoor persistence with malicious payloads (shell commands, SSH key injection, hidden root users) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · README.md (reported line 20)May include surrounding context.

d market analysis. This skill enables querying niche market information, analyzing competition, evaluating demand, and identifying profitable opportunities in US, Japan, and Germany markets.

Quick Start

1. Setup API Key

bash
export LINKFOXAGENT_API_KEY="your_api_key_here"

For persistent configuration, add to your shell profile (~/.bashrc, ~/.zshrc, or ~/.profile):

bash
echo 'export LINKFOXAGENT_API_KEY="your_api_key_here"' >> ~/.bashrc
source ~/.bashrc

2. Usage in OpenClaw

Activate the skill by mentioning Amazon market research or product selection:

text
User: "Analyze the bluetooth charger market in the US"
User: "Find low-competition niches for kitchen gadgets"
User: "What are the best opportunities in German market for coffee products?"

The skill automatically:

  • Translates keywords to target market language
  • Queries Amazon marketplace data
  • Analyzes competition and demand
  • Presents actionable insights

3. Command-Line Usage

The Pyt

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README instructs activation via broad natural-language phrases like 'Amazon market research' or 'product selection' without defining boundaries, exclusions, or confirmation requirements. In an agent environment, this can cause over-broad auto-invocation and unintended use of the skill on queries the user did not clearly intend to send to an external market-analysis service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill states it will automatically translate keywords and query Amazon marketplace data, but it does not clearly warn that user-provided queries may be transmitted to an external API. This creates a privacy and data-handling risk because users may unknowingly disclose sensitive business plans, product ideas, or proprietary research terms to a third party.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill documents use of environment secrets, network access, and downstream file/output generation, but the manifest does not declare any explicit permission or allowed-tools scope. This weakens least-privilege enforcement and can allow the skill to be invoked with broader capabilities than users or the platform can easily audit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description contains broad activation language like market research, product selection, niche analysis, and competitive intelligence, which can match many ordinary user requests. Over-broad triggering increases the chance the skill is selected unexpectedly and user queries are routed to an external service without sufficiently specific intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill describes sending user-supplied keywords and authenticated requests to a third-party API endpoint, but it does not clearly warn that query contents will leave the local environment. This creates a privacy and data-handling risk, especially if users include sensitive business plans, proprietary product ideas, or personal data in their queries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation explicitly tells users to run echo $LINKFOXAGENT_API_KEY, which displays a sensitive credential on screen and may expose it through terminal recording, screen sharing, shell audit tooling, or operational logs. While this is framed as a setup verification step, encouraging direct plaintext disclosure of an API key is an unsafe secret-handling practice.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/API-Overview.md (reported line 102)May include surrounding context.

Synchronous Requests

For quick operations (<1 second response time):

bash
curl -X POST https://test-tool-gateway.linkfox.com/endpoint \
  -H "Authorization: ${LINKFOXAGENT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"param": "value"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · references/API-Overview.md (reported line 197)May include surrounding context.

md
def api_request_with_retry(url, data, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = requests.post(url, json=data, headers=headers)
            if response.status_code == 200:
                return response.json()
            elif response.status_code == 429:

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · references/API-Overview.md (reported line 376)May include surrounding context.

md
def api_request_with_retry(url, data, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = requests.post(url, json=data, headers=headers)
            if response.status_code == 200:
                return response.json()
            elif response.status_code == 429:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/API-Overview.md (reported line 394)May include surrounding context.

md
KEYWORD="bluetooth speaker"
COUNTRY="US"

curl -X POST "https://test-tool-gateway.linkfox.com/jiimore/getNicheInfoByKeyword" \
  -H "Authorization: ${LINKFOXAGENT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/jiimore_client.py (reported line 143)May include surrounding context.

python
payload = query.to_dict()

        try:
            response = requests.post(
                url, json=payload, headers=self.headers, timeout=timeout
            )
            response.raise_for_status()

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
61% confidence
Finding

The README mixes English instructions with tool references such as '@Python沙箱' and '@网页检索', which could reflect a locale-specific convention. Because no language or locale choice is offered and no justification is provided, this may conflict with a policy against forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents sending user-supplied keywords plus authenticated requests to an external third-party endpoint, but provides no user-facing disclosure or consent guidance. In a shopping research context, queries may still contain sensitive business intent or proprietary product ideas, so silent transmission creates a privacy and data-governance risk even if it is not direct code execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction to translate queries into the target market language without offering user choice can alter user input before transmission and may cause unintended disclosure, semantic drift, or incorrect analysis. In this market-intelligence context, mistranslation can also expose proprietary search intent in another language without the user realizing the transformation occurred.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code performs an outbound HTTP POST to a remote API and transmits the user's keyword query along with an authorization credential. While the module docstring says it provides API access, there is no explicit user-facing warning at the point of execution about transmitting user input to an external service.

Content

No source excerpt is available for this finding.