Biomolecular Structure Prediction

• Outcome: Review
• Latest audit: Sep 16, 2026 · 4:08 AM UTC
• Version: 1.0.8

Overview

The skill has a legitimate SciMiner structure-prediction purpose, but it tells agents to run invocation code from mutable remote Markdown documentation, which needs review before installation.

Install only if you trust the SciMiner documentation host to remain correct and uncompromised, and prefer a version that bundles reviewed request-building logic locally or verifies remote docs before use. Treat uploaded biomolecular inputs and the SciMiner API key as sensitive, and confirm destination endpoints before sending files.

A.I.G

Vulnerability Patterns

• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

• Location: SKILL.md:32

Finding

Unpinned Remote Documentation Can Supply Executable Invocation Code

Content

View full analysis

`Chai-1_api_doc.md` - `Boltz-2` -> `Boltz-2_api_doc.md` - `AlphaFold3` -> `AlphaFold3_api_doc.md` - If the user explicitly requests a covalent-ligand workflow, use the corresponding `Chai-1-Covalent_api_doc.md`, `Boltz-2-Covalent_api_doc.md`, or `AlphaFold3-Covalent_api_doc.md`. The agent MUST: 1. Resolve the selected tool's Markdown file and read it before every invocation. 2. Never invent `provider_name`, `tool_name`, parameter names, enum values, upload-field names, content type, or submission flow from memory. 3. Extract and follow the selected doc section's exact: - Base URL - API endpoint - Content-Type - Authentication header - Tool Name - Method - Parameter table, including required fields and enum values - File-upload instructions and example code 4. Choose the correct section if the selected doc contains multiple tool variants, such as standard vs covalent workflows or inline inputs vs file uploads. 5. Cite the selected Markdown doc as the payload source in summaries. [...] 2. Read the corresponding Markdown file from `https://sciminer.tech/tool_api_files/`. 3. If the request includes covalent chemistry, switch to the corresponding covalent Markdown doc. 4. Choose the doc section that matches the user's input shape. 5. Collect any missing required parameters from the user. 6. Upload required file inputs exactly as described by the selected Markdown do ...[truncated 3424 chars]

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 114)May include surrounding context.

md

name: structure-prediction
description: Biomolecular structure prediction tools for Chai-1, Boltz-2, and AlphaFold3 via SciMiner APIs.
credential_files:
   - ~/.config/sciminer/credentials.json
---

# Structure Prediction Skill

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 88% confidence

Finding

The skill requires the agent to read remote Markdown documentation before every invocation and to write or run invocation code directly from that documentation. That creates a prompt/code supply-chain risk: if the remote docs are compromised or contain unsafe example code, the agent may execute attacker-controlled instructions, potentially leading to data exfiltration, unsafe file access, or arbitrary outbound requests using available credentials.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md

5. Collect any missing required parameters from the user.
6. Upload required file inputs exactly as described by the selected Markdown
   doc and replace local paths with returned `file_id` values.
7. Write or run the invocation code directly from the selected Markdown doc's
   base-information block, parameter table, file-upload instructions, and
   example code. Do not apply a shared invocation template or local registry
   abstraction in this skill.

Static analysis

No suspicious patterns detected.