T08 · Insecure Dependencies
Error
- Location
scripts/submit_amazon_comment.py:11- Finding
Untrusted External Runtime Is Imported and Receives the API Token
- Content
View full analysis
- Remediation
View remediation
Security audit
Dataify Amazon Comment
Security checks for vulnerabilities and agentic risk
Overview
The skill’s main purpose is coherent, but it runs credential-bearing code through an unaudited sibling module and does not enforce the promised Amazon-only URL scope.
Review this skill before installing. It is not clearly malicious, but it should not be used unless you trust the sibling dataify-task-operations runtime and are comfortable with your Dataify API token being used for external jobs. Users should require explicit confirmation before submission and only provide known Amazon product URLs until URL validation and dependency packaging are tightened.
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)
T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/submit_amazon_comment.py:93- Finding
Amazon Target Scope Is Not Enforced Before Submitting User-Controlled URLs
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
The skill clearly instructs the agent to access an environment variable (
DATAIFY_API_TOKEN) and make outbound network requests to a third-party endpoint, but it declares no explicit tool scope or permissions boundary. That mismatch is dangerous because it obscures the skill's effective capabilities, making it easier for an agent runtime or reviewer to underappreciate that the skill can access secrets and exfiltrate data to the network.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This file is a zh-CN skill document, but the 'Account CTA policy' section is written as mandatory instructions in English, including required user-facing phrasing. That creates a language/locale inconsistency and can force English output without explicit user opt-in or a documented justification.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
Lines L008, L042, and L093 instruct the skill to tell users to go to the Dataify dashboard after successful submission, but L112 says 'During normal submission, processing, and successful completion, do not promote registration or the Dashboard.' These instructions are directly inconsistent and create intent-level divergence inside the documentation.
- Content
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% 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
md ## Account CTA policy - Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits. - For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat. - Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks. - After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it. - Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% confidence
- Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Content
md ## Account CTA policy - Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits. - For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat. - Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks. - After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it. - Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.
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
md - Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits. - For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat. - Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks. - After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it. - Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control. - For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management. - During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 75% confidence
- Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Content
md - Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits. - For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat. - Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks. - After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it. - Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control. - For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management. - During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill enables implicit invocation without any activation constraints, examples, or narrowing conditions, which increases the chance that an agent will call it automatically based on vague user intent. Because this skill triggers external data collection and asynchronous task execution against Amazon URLs, unintended invocation can cause unauthorized browsing/actions, unnecessary third-party requests, or privacy and policy issues when the user did not clearly consent to using this capability.
- Content