Back to skill

Security audit

Sellersprite Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon marketplace research helper, with some setup and language/default-market caveats but no evidence of hidden or destructive behavior.

Install only if you are comfortable giving the SellerSprite client access to your SellerSprite API key and marketplace research queries. Use a virtual environment, pin and verify the `sellersprite-cli` package when possible, confirm the target marketplace instead of relying on the US default, and avoid storing or sharing reviewer-identifying data unless necessary.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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 (1)

T08 · Insecure Dependencies

Warning
Location
agent-instructions.md:37
Finding

Unpinned Third-Party Package Installation

Content
View full analysis

Vulnerability Details

File Location: agent-instructions.md, lines 37-39
Vulnerability Type: Unpinned third-party dependency installation
Risk Level: Medium

Complete Code Snippet:

bash
pip install sellersprite-cli

Technical Analysis

The installation command resolves and installs the latest available version of sellersprite-cli from pip's configured package index. It does not specify an exact reviewed version, verify cryptographic hashes, identify a trusted index, or require an isolated environment.

Python package installation may execute package-controlled build or installation logic. Consequently, a compromised publisher account, malicious replacement release, dependency-confusion condition, compromised package index, or unexpected upstream change could introduce code that was not present during this Skill audit.

This finding is a supply-chain weakness rather than evidence that the current sellersprite-cli package is malicious.

Attack Path

  1. An attacker compromises the package publisher, package-index account, distribution channel, or a transitive dependency.
  2. The attacker publishes a malicious release that satisfies the unrestricted package name.
  3. A user or agent follows the documented pip install sellersprite-cli instruction.
  4. pip resolves the attacker-controlled or compromised release.
  5. Malicious package build, installation, import, or runtime logic executes with the privileges of the account running pip.
  6. That code may access files and credentials available to the user or manipulate subsequent SellerSprite client and MCP operations.

Impact Assessment

Successful exploitation can obtain code execution with the privileges of the user performing the installation. The accessible scope may include that user's files, environment variables, Python environment, SellerSprite configuration and API credentials, and network access permitted to the process.

The ins ...[truncated 258 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the dependency to an exact version that has undergone review:
    bash
    python -m pip install sellersprite-cli==<reviewed-version>
    
  2. Publish and verify hashes through a locked requirements file:
    text
    sellersprite-cli==<reviewed-version> \
        --hash=sha256:<verified-distribution-hash>
    
    Install it with:
    bash
    python -m pip install --require-hashes -r requirements.txt
    
  3. Pin and hash all transitive dependencies, preferably using a reproducible lock-generation process.
  4. Explicitly document the trusted package index and avoid untrusted extra indexes:
    bash
    python -m pip install --index-url https://pypi.org/simple --require-hashes -r requirements.txt
    
  5. Recommend installation inside a dedicated virtual environment using a non-privileged account.
  6. Verify package publisher identity, release provenance, signatures or attestations where available, and the integrity of downloaded distributions before adoption.
  7. Establish a controlled dependency-update process that reviews and tests each new version before changing the pin.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (29)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The entire skill index and invocation guidance are presented only in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

该文件的技能描述、调用说明和示例均固定为中文,且未声明可根据用户偏好切换语言,也未说明中文为必要的合规或区域性要求。按照语言/locale 政策,这可能构成未获用户选择的语言强制。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The tactical skills are described as being triggered by mentioning a skill name in normal conversation, but the file does not define strict invocation boundaries, disambiguation rules, or confirmation requirements. In an agent setting, this can cause accidental tool execution from ordinary user phrasing, leading to unintended marketplace queries, noisy results, and possible downstream automation based on the wrong workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example trigger phrase is a common natural-language shopping research request and is shown as sufficient to activate a tactical skill. Because the example lacks any trigger boundary or opt-in syntax, an agent may overmatch ordinary conversation and execute the '新品快速爆发' workflow when the user did not intend to invoke a predefined skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents all operational guidance and command usage in Chinese, which effectively forces a specific language for users without any opt-in or alternative. The stated policy for this audit flags language or locale constraints unless the skill offers a choice or clearly justifies the restriction as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is authored entirely in Chinese and prescribes Chinese-formatted output without offering a user-selectable language or documenting a strict locale requirement. In a multilingual agent environment, this can cause user misunderstanding, reduce operator oversight, and lead to incorrect execution of ad-budget or bidding recommendations, though it is not a classic code-execution or data-exfiltration issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructions, headings, and output requirements are entirely in Chinese, which effectively imposes a specific language on users. The file does not provide an opt-in, alternative language, or justification that this is a region-specific skill, so it 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
94% confidence
Finding

The skill is written entirely in Chinese and specifies output structures and recommendations in Chinese, with no indication that the user can choose another language. This is a natural-language locale constraint that lacks opt-in or justification, which matches the policy-violation criteria for SQP-3.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is written entirely in Chinese and prescribes Chinese-language interaction and report structure without offering any language negotiation or opt-in. In a multi-user or multi-tenant agent setting, this can override user expectations, reduce transparency, and cause users to miss important analytical caveats or security-relevant details if they cannot read the forced language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill specification, including headings, usage, execution steps, and output instructions, is written exclusively in Chinese, which implies a fixed language/locale for interaction. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language instructions and output requirements are entirely in Chinese, which effectively forces a specific language for interaction and reporting. The file does not state that the skill is region-specific or provide users an option to choose another language, matching the language/locale policy concern in SQP-3.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown skill specifies its instructions, usage, and output requirements only in Chinese, which can amount to forcing a specific language without user opt-in. The file does not indicate that the skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown skill forces a specific language for all instructions, triggers, and safety notes, which can violate a language/locale policy when no user opt-in or justification is provided. The file contains no indication that Chinese is optional, selectable, or required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill hard-codes the marketplace parameter to "US" without indicating that this is a default or allowing user confirmation. This can cause the agent to run research against the wrong regional market, producing misleading business decisions or unintended data access scope, though it is not a classic security exploit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill hard-codes the marketplace to "US" in its default parameter block without indicating that locale should be selected based on the user's actual target market. In an e-commerce research workflow, this can cause the agent to query the wrong regional dataset, producing misleading market intelligence or exposing user intent to an unintended marketplace context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language instructions, headings, and trigger examples are all Chinese, and there is no indication that users may opt into another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

At L47, the document explicitly states that keyword_research cannot do batch queries and must be called in parallel per keyword. At L53, it recommends using a keywordList array to batch query multiple seed keywords, which directly conflicts with the earlier limitation and creates contradictory operator guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese, and nowhere indicates that the skill is Chinese-only or provides an opt-in language/locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill is written in Chinese and provides no indication that users may choose another language or locale. Per the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire skill is written in Chinese and provides all trigger phrases, instructions, and warnings only in Chinese, with no indication that users may interact in other languages or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown skill specifies its instructions, headings, and output expectations exclusively in Chinese, which can amount to a language/locale constraint for users who have not opted into that language. The file does not indicate that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown skill explicitly instructs calling the review API to retrieve comment data, but it does not disclose any privacy or data-handling considerations to the user. Under the markdown-file criteria for SQP-2, behaviors that affect data or privacy should be accompanied by a warning in the skill description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructions and required report structure are entirely in Chinese, and the file does not indicate that the output language should follow the user's preference or offer an opt-in choice. This can violate language/locale policy when users expect responses in another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructions, headings, and usage guidance are all presented in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to Chinese-speaking contexts. This can conflict with language/locale policy when a skill implicitly forces a language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill explicitly instructs retrieval of review titles, full review content, reviewer identifiers, and review timestamps, but provides no warning or minimization guidance for handling third-party user-generated data. While this is not an exploit primitive by itself, it creates unnecessary privacy exposure and increases the chance that personal or sensitive information from external reviewers will be processed, retained, or surfaced without need.

Content

No source excerpt is available for this finding.