Back to skill

Security audit

Dreamer

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its drug-design purpose, but it needs review because it automatically runs broad workflows, persists scraped web content into agent context, and loads mutable or unsafe model artifacts.

Install only in an isolated sandbox without credentials or sensitive private molecule data unless you first review and constrain the workflows. Disable or gate the web monitor, treat latest_research.txt as untrusted reference data, pin model/checkpoint sources, and require explicit approval before training, scraping, or writing outputs.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (4)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:15
Finding

Untrusted Web Content Is Persisted and Automatically Loaded into Agent Context

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/spider/web_monitor.py:77
Finding

ArXiv Intelligence Feed Uses Unencrypted HTTP Transport

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
scripts/ddllms_v1/ddllms_condition_v1.py:5
Finding

Normal Workflows Download Mutable and Unpinned Third-Party Model Artifacts

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/vis_classifier/BLIP_embedding_model.py:25
Finding

PyTorch Checkpoint Is Loaded Through Potentially Unsafe Pickle Deserialization

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (37)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The Chinese description claims an end-to-end drug/material design platform, but the detected behavior is limited to generic statistical binning and histogram plotting. In this context, the inflated description makes the skill more dangerous because it operates in a chemistry/drug-design setting where users may trust it with sensitive IP and consequential decisions.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill explicitly instructs reading local files, writing to knowledge_data/latest_research.txt, and performing network scraping, yet declares no tool scope or permission boundaries. This creates an overbroad execution surface where the agent may access files or external resources without explicit user awareness or least-privilege controls.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The visible natural-language description is written entirely in Chinese and presents the skill as a Chinese-language development guide without indicating that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in is a policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs web_monitor.py to scrape external sources and write results into knowledge_data/latest_research.txt without explicit user warning or consent. This is dangerous because it combines outbound network activity with local state modification, enabling unanticipated data ingestion, persistence, and possible contamination of later analyses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The routing table uses broad intent triggers such as generation, classification, recommendation, optimization, and visualization without clear exclusions, tie-breakers, or authorization checks. This can cause the agent to enter overly powerful workflows unexpectedly, especially when combined with file, training, or network-capable submodules.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are very broad generic phrases such as '画图' and '生成热力图', which can overlap with common user requests outside the intended molecular-analysis scope. In an agent system, this can cause the visualization skill to activate unexpectedly, pull data from other modules, or respond in contexts where the user did not intend this specialized workflow, increasing the risk of data leakage, misrouting, or unsafe cross-tool invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions are phrased very broadly, such as requests to 'find the best molecules' or 'filter generated molecules', which can match many normal chemistry-domain queries without strong scoping or user-intent validation. In an agentic system for drug-delivery and molecular design, this can cause the skill to activate unexpectedly, route sensitive chemistry tasks automatically, and bypass safer or more context-appropriate handling paths.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are overly broad and can cause the molecule-generation workflow to be invoked for loosely related requests such as generic 'train a model' or 'generate a batch of molecules' prompts without sufficient gating. In a chemistry/drug-delivery context, unintended invocation increases risk because the skill can produce and export large sets of novel chemical structures that may bypass higher-level review or safety checks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger conditions are phrased very broadly (e.g. any request to predict molecular properties or explain a property), without clear input boundaries, authorization checks, or domain constraints. In an agent setting this can cause unintended invocation on ambiguous prompts, leading the system to process unvalidated molecular data, run expensive analysis pipelines, or produce sensitive decision-support outputs in contexts where the user did not explicitly request this exact workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger conditions are broad natural-language phrases like '微调模型让它更准' and '加载我的反馈数据优化模型', which can cause the skill to activate in loosely related contexts without clear scoping or authorization checks. In a system that performs model fine-tuning on private datasets and human feedback, overbroad activation increases the risk of unintended training actions, misuse of sensitive data, or invocation of expensive/high-impact workflows from ambiguous user requests.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The return top_values, top_indices statement is misindented outside get_top_n_values, which means the documented extraction logic is not actually part of the function and the file will not behave as intended. In practice this can cause import/runtime failure or make downstream code skip similarity-ranking logic, leading to incorrect analysis outputs in a chemistry decision-support pipeline.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The Google News RSS URL forces hl=en-US, gl=US, and ceid=US:en, which imposes a specific language and locale policy in the skill behavior. The file does not offer any user opt-in or configuration for alternative locales, nor does it document why a U.S. English-only feed is required.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The comments label these routines as 'Training the model', 'Evaluate the model', and a 'Main function to orchestrate training and evaluation', but both train_model and evaluate_model use pyg_method without accepting it as a parameter. In main, pyg_method is initialized as a local variable at L79, so the documented orchestration contradicts the actual code behavior: these functions are not self-contained and will fail unless a global variable exists.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file presents the skill description primarily in Chinese and embeds an English natural-language input example, but it does not indicate whether the skill supports user language selection or requires a particular language. This can constitute a language-policy issue because the skill appears to impose language expectations without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The workflow explicitly saves generated SMILES candidates to .npy files but does not warn users that potentially sensitive or hazardous molecular outputs will be written to disk. In this domain, silent persistence can create audit, data-handling, and downstream misuse risks because generated chemical candidates may be reused, redistributed, or processed without user awareness.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language instructions and user-facing trigger descriptions are entirely in Chinese, which can impose a language constraint on users and downstream agents. The file does not indicate that Chinese is optional, user-selected, or required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file's natural-language comments are written in Chinese throughout, which imposes a specific language on maintainers and reviewers without indicating any user choice or documented locale requirement. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file contains natural-language comments in Chinese only (for example at L02, L07, and L15), which imposes a specific language on maintainers and users without offering any language choice or documenting a locale-specific need. This matches the policy category for language or locale constraints expressed in natural language.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/ddllms_v1/dd_tokenzier_base_v1.py (reported line 32)May include surrounding context.

python
return len(self.smiles_strings)
    def __getitem__(self, i: int) -> torch.Tensor:
        encodings = self._encode(self.smiles_strings[i])
        return torch.LongTensor(getattr(encodings, self._id_key))
@dataclass(init=True, repr=True, eq=False, frozen=False)
class LMDataModule(LightningDataModule):
    """Lightning data module for autoregressive language modeling.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The code configures a ModelCheckpoint callback to save model artifacts under the user-supplied checkpoint path, which is a file-writing operation. There is no confirmation prompt, print/log message, or inline warning indicating that training will persist files to disk at this location.

Content

No source excerpt is available for this finding.