Back to skill

Security audit

AI 股场

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent with a simulated stock-trading and social platform, but it can submit account actions and has concrete credential-handling and shell-injection risks users should review before installing.

Review this skill before installing. Use it only with an account and API key you are comfortable exposing to this platform, keep config.json private, do not point baseUrl at untrusted hosts, and require manual confirmation before any trade, post, comment, or vote. The shell scripts should be hardened before use in an autonomous or shared environment.

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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/trade.sh:48
Finding

Bash Arithmetic Evaluation Enables Local Command Injection

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/_common.sh:27
Finding

Configurable API Destination Can Exfiltrate the Bearer Token

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/register.sh:51
Finding

Registration Exposes the Full API Key in Output and Plaintext Configuration

Content
View full analysis
Remediation
View remediation
"$tmp_file" || exit 1 chmod 600 "$tmp_file" mv "$tmp_file" "$CONFIG_FILE" ``` 4. Avoid placing secrets in command-line arguments, since process listings and shell histories may capture them. 5. Support an operating-system keyring, secret manager, or protected environment-based credential provider where available. 6. Document that `config.json` must not be committed to source control. 7. Add `config.json` to `.gitignore`. 8. Check file ownership and permissions before reading the token, and warn or refuse to proceed if the file is accessible by group or other users. 9. Ensure application logs and Agent transcripts redact values matching the API-key format. 10. Provide token rotation and revocation guidance for suspected disclosure. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (27)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trade section documents direct execution commands but does not warn that these actions place orders with account consequences, nor does it instruct the agent to obtain clear user consent before submission. In an autonomous-agent context, this omission materially increases the risk of accidental or unauthorized transactions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README explicitly encourages account-impacting actions such as buying stocks and publishing analysis, but provides no warning about financial risk, irreversible trade effects, or the need for user confirmation. In the context of an AI-only trading platform, this omission increases the chance that users enable autonomous trading behavior without understanding that the skill can trigger real or simulated account actions with consequential outcomes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill maps a very broad natural-language trigger like '买入/卖出xxx' directly to a trade execution command, which is a high-impact action affecting an account and portfolio. Without explicit confirmation, parameter validation, or a read-only preview step, an agent could place unintended orders from ambiguous, partial, or conversational user input.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The posting, commenting, and reaction features send user- or agent-generated content to an external platform, but the skill does not warn that this content may be public or shared with third parties. Users may unknowingly disclose sensitive strategies, account intentions, identifiers, or proprietary analysis through these actions.

Content

No source excerpt is available for this finding.

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 · scripts/_common.sh (reported line 40)May include surrounding context.

sh
return 1
    fi
    
    curl -s -X "$method" \
        -H "Authorization: Bearer $api_key" \
        -H "Content-Type: application/json" \
        ${data:+-d "$data"} \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The function performs an outbound HTTP request and includes the bearer API key in the Authorization header. While the code comments indicate this is an API helper, there is no user-facing warning, prompt, or logging in this file that discloses that credentials and request data may be transmitted to a remote service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script's comments, help text, and user-facing output are in Chinese, and there is no option to select another language or explanation that the skill is intentionally Chinese-only. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Natural-language strings throughout the script, including help output and status messages, are fixed in Chinese. This imposes a language choice on users without opt-in or an alternative locale, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Comments, help text, and runtime output are all presented in Chinese, with no opt-in or alternative locale handling. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This shell script collects user-provided post content and sends it to an external endpoint via api_request POST "/v1/agent/posts". Although posting is the script's purpose, the file itself provides no explicit warning or disclosure that the supplied content will be transmitted to a remote service, which is a safety-relevant operation involving user data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script's comments and help text presented to users are written only in Chinese, which imposes a specific language without opt-in or documented justification. Under the stated policy, forced language/locale behavior is a natural-language policy violation unless the skill offers a choice or clearly documents the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This shell script presents its help and user-facing output in Chinese only, including the description and usage text. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in or a clearly documented justification.

Content

No source excerpt is available for this finding.

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 · scripts/register.sh (reported line 44)May include surrounding context.

sh
# 发送请求 (注册不需要 API Key)
BASE_URL=$(get_config "baseUrl" "https://arena.wade.xylife.net/api")
RESPONSE=$(curl -s -X POST \
    -H "Content-Type: application/json" \
    -d "$REQUEST" \
    "${BASE_URL}/v1/register")

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script prints the returned API key directly to stdout and tells the user to save it in config.json without clearly warning that it is a sensitive credential. This increases the chance of accidental exposure through terminal logs, shell history capture, screen sharing, CI logs, or insecure file permissions on the saved config.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script’s comments, help text, and runtime messages are presented in Chinese only, including the usage output and success/failure notices. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or documented justification is a reportable issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The skill specifies user invocation phrases entirely in Chinese, such as '当用户说' followed by Chinese trigger examples, without indicating that other languages are supported or that Chinese is required for a justified regional reason. This can be interpreted as a language constraint without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The file's natural-language labeling is Chinese-only, and all user-facing status/error strings shown here are also in Chinese. There is no indication in this file that the user can opt into another language or that the locale restriction is explicitly documented as a justified regional constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The function reads the apiKey from configuration and uses it for authenticated requests, which is access to sensitive credentials. This file does not provide an explicit warning or disclosure about handling stored credentials beyond setup instructions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

At L25 the script sends a network request to a configured remote API using curl, but the only indication is an internal comment at L23 saying authentication is not needed. There is no user-facing notice in help output or runtime messaging that the script contacts an external service, which reduces transparency for a data-fetching operation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script sends a user-provided market parameter to a remote API endpoint without clearly disclosing that external network communication will occur. While the transmitted value is not highly sensitive by itself, silent network access can expose usage patterns, trigger unexpected data egress, and surprise users running the skill in restricted or privacy-sensitive environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This shell script makes a network request to retrieve portfolio information, which involves transmitting account-related query data and exposing sensitive financial data in output. Although the script prints results after the call, there is no prior disclosure, comment, or warning explaining that remote account data will be accessed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's natural-language interface, including usage text and status/error messages, is entirely in Chinese. This imposes a specific language on users without opt-in or explanation, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This shell script performs an HTTP request to a remote API using curl, which transmits request metadata to an external service. Although the script's purpose is to list posts, the network access itself is not disclosed at the point of execution by a prompt, log message, or explanatory comment, so users may not realize it contacts a remote host.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

All user-facing help and status messages are presented in Chinese, with no indication that language is configurable or limited by design. This can violate language/locale policy when skills are expected to avoid 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
89% confidence
Finding

The script sends the user-supplied --codes value to a remote HTTP endpoint via curl, but there is no confirmation prompt or user-facing notice at the point of transmission. Although fetching quotes is the script's purpose, the file itself does not disclose that the provided symbols will be sent to an external service.

Content

No source excerpt is available for this finding.