High Risk
学术文献智能工具包 - 高效、系统性的学术文献分析与知识管理工具
H:4 D:4 A:3 C:1
⚠️ Hazard Flags
EXEC CODE_EXEC FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES CREDS_BROWSER ACT_POST_PUBLIC PI_WEB PI_DOCUMENTS
📋 Capabilities
Execution
- ✅ Shell execution
- ✅ Code execution
- ✅ Install dependencies
- ❌ Persistence
- Privilege: user
Filesystem
- ✅ Read workspace
- ✅ Write workspace
- ✅ Read home
- ❌ Write home
- ❌ Read system
- ✅ Delete
Network
- Egress: any
- ❌ Ingress
Credentials
- ✅ Environment vars
- ✅ Credential files
- ✅ Browser data
- ❌ Keychain
Actions
❌ send messages✅ post public❌ purchase❌ transfer money❌ deploy❌ delete external
🔒 Containment
Level: maximum
Required:
- APPROVE_POST: Can post publicly
- SANDBOX_CONTAINER: Code execution capability
Recommended:
- LOG_ACTIONS: Audit trail for all actions
⚡ Risks
Prompt injection patterns detected in: SKILL.md, shared/ai-provider.ts high
Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.
Unauthorized tool use: INSTRUCTED_GIT_CLONE_AND_BUILD medium
Mitigation: Use pre-built packages or vendored dependencies instead of cloning repos
Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL, MCP_SQL_BLIND critical
Mitigation: Remove embedded script tags and encoded payloads.
Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION low
Mitigation: Provide clear, detailed description of skill functionality
Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_BASE64_AND_NETWORK critical
Mitigation: Do not access credential files or sensitive system files
Want a deeper analysis?
This report was generated by static analysis. Get an LLM-powered deep review with behavioral reasoning and attack surface mapping.
🧠 Deep Analysis — $5.00🚨 Incident Response
Kill switch: Stop the agent process
Containment: Review logs for unexpected actions
Recovery: Depends on skill capabilities
📄 Raw SSDS JSON click to expand
{
"meta": {
"document_id": "ssds:auto:scholargraph:1.0.0",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-28T09:22:28.529Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "ScholarGraph",
"version": "1.0.0",
"format": "agent_skill",
"description": "学术文献智能工具包 - 高效、系统性的学术文献分析与知识管理工具",
"publisher": "ClawHub",
"source": {
"channel": "clawhub",
"slug": "scholargraph",
"owner": "josephyb97",
"downloads": 572,
"stars": 1
},
"artifact": {
"sha256": "8c4e3bc9aeabf5c59e5f5dad90d8ec4c1930db19b7b23d5299179ec4105f5e1b",
"hash_method": "files_sorted"
}
},
"capabilities": {
"execution": {
"can_exec_shell": true,
"can_exec_code": true,
"privilege_level": "user",
"can_install_deps": true,
"can_persist": false
},
"filesystem": {
"reads_workspace": true,
"reads_user_home": true,
"reads_system": false,
"writes_workspace": true,
"writes_user_home": false,
"writes_system": false,
"can_delete": true
},
"network": {
"egress": "any",
"ingress": false
},
"credentials": {
"reads_env_vars": true,
"reads_credential_files": true,
"reads_browser_data": true,
"reads_keychain": false
},
"services": [],
"actions": {
"can_send_messages": false,
"can_post_public": true,
"can_purchase": false,
"can_transfer_money": false,
"can_deploy": false,
"can_delete_external": false
},
"prompt_injection_surfaces": [
"web",
"documents"
],
"content_types": [
"general"
]
},
"hazards": {
"hdac": {
"H": 4,
"D": 4,
"A": 3,
"C": 1
},
"flags": [
"EXEC",
"CODE_EXEC",
"FS_READ_WORKSPACE",
"FS_READ_USER",
"FS_WRITE_WORKSPACE",
"FS_DELETE",
"NET_EGRESS_ANY",
"CREDS_ENV",
"CREDS_FILES",
"CREDS_BROWSER",
"ACT_POST_PUBLIC",
"PI_WEB",
"PI_DOCUMENTS"
],
"custom_flags": [
{
"code": "PROMPT_INJECTION",
"name": "Prompt Injection Risk",
"description": "Contains prompt injection patterns in: SKILL.md, shared/ai-provider.ts"
},
{
"code": "FILE_DELETE",
"name": "File Deletion",
"description": "Can delete files in: paper-viz/scripts/ppt-exporter.ts"
},
{
"code": "TOOL_ABUSE",
"name": "Unauthorized Tool Use",
"description": "INSTRUCTED_GIT_CLONE_AND_BUILD: Instructs agent to clone and potentially build from source"
},
{
"code": "SOCIAL_ENGINEERING",
"name": "Social Engineering Risk",
"description": "SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION: Skill description is too vague or missing"
},
{
"code": "COMMAND_INJECTION",
"name": "Command Injection Risk",
"description": "MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL, MCP_SQL_BLIND: Script tags, VBScript, or encoded script data URIs"
},
{
"code": "DATA_EXFILTRATION",
"name": "Data Exfiltration Risk",
"description": "DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_BASE64_AND_NETWORK: Accessing sensitive system or credential files"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 6 security patterns (12 vendored rule hits). Review recommended."
},
"rationale": {
"H": "H4: Critical: Privilege escalation or malware detected",
"D": "D4: Critical: Credential theft or data exfiltration",
"A": "A3: External actions (deploy/message/post)",
"C": "C1: General content"
}
},
"containment": {
"level": "maximum",
"required": [
{
"control": "APPROVE_POST",
"reason": "Can post publicly"
},
{
"control": "SANDBOX_CONTAINER",
"reason": "Code execution capability"
}
],
"recommended": [
{
"control": "LOG_ACTIONS",
"reason": "Audit trail for all actions"
}
],
"uncontained_risk": "Risk level depends on manual review of actual capabilities."
},
"risks": {
"risks": [
{
"risk": "Prompt injection patterns detected in: SKILL.md, shared/ai-provider.ts",
"severity": "high",
"mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
},
{
"risk": "Unauthorized tool use: INSTRUCTED_GIT_CLONE_AND_BUILD",
"severity": "medium",
"mitigation": "Use pre-built packages or vendored dependencies instead of cloning repos"
},
{
"risk": "Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL, MCP_SQL_BLIND",
"severity": "critical",
"mitigation": "Remove embedded script tags and encoded payloads."
},
{
"risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION",
"severity": "low",
"mitigation": "Provide clear, detailed description of skill functionality"
},
{
"risk": "Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_BASE64_AND_NETWORK",
"severity": "critical",
"mitigation": "Do not access credential files or sensitive system files"
}
],
"limitations": [
"Static analysis only - runtime behavior not verified"
]
},
"incident_response": {
"kill_switch": [
"Stop the agent process"
],
"containment": [
"Review logs for unexpected actions"
],
"recovery": [
"Depends on skill capabilities"
]
},
"evidence": [
{
"evidence_id": "EV:file-1",
"type": "file_excerpt",
"title": "_meta.json",
"file_path": "_meta.json"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "workflows/review-to-graph.ts",
"file_path": "workflows/review-to-graph.ts"
},
{
"evidence_id": "EV:file-3",
"type": "file_excerpt",
"title": "test/scripts/test-advanced-features.ts",
"file_path": "test/scripts/test-advanced-features.ts"
},
{
"evidence_id": "EV:file-4",
"type": "file_excerpt",
"title": "test/scripts/paper-viz.test.ts",
"file_path": "test/scripts/paper-viz.test.ts"
},
{
"evidence_id": "EV:file-5",
"type": "file_excerpt",
"title": "SKILL.md",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:file-6",
"type": "file_excerpt",
"title": "shared/validators.ts",
"file_path": "shared/validators.ts"
},
{
"evidence_id": "EV:file-7",
"type": "file_excerpt",
"title": "shared/utils.ts",
"file_path": "shared/utils.ts"
},
{
"evidence_id": "EV:file-8",
"type": "file_excerpt",
"title": "shared/types.ts",
"file_path": "shared/types.ts"
},
{
"evidence_id": "EV:file-9",
"type": "file_excerpt",
"title": "shared/errors.ts",
"file_path": "shared/errors.ts"
},
{
"evidence_id": "EV:file-10",
"type": "file_excerpt",
"title": "shared/ai-provider.ts",
"file_path": "shared/ai-provider.ts"
},
{
"evidence_id": "EV:cisco-1",
"type": "file_excerpt",
"title": "MCP_SCRIPT_TAGS [HIGH] test/scripts/paper-viz.test.ts:229: a.metadata.title = 'Test <script>alert(\"xss\")</script>';",
"file_path": "test/scripts/paper-viz.test.ts"
},
{
"evidence_id": "EV:cisco-2",
"type": "file_excerpt",
"title": "INSTRUCTED_GIT_CLONE_AND_BUILD [MEDIUM] SKILL.md:187: git clone https://github.com/Josephyb97/ScholarGraph.git",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-4",
"type": "file_excerpt",
"title": "SOCIAL_ENG_ANTHROPIC_IMPERSONATION [MEDIUM] SKILL.md:174: - **Multi-AI Provider Support**: 15+ AI providers including OpenAI, Anthropic, D",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-5",
"type": "file_excerpt",
"title": "COMMAND_INJECTION_EVAL [CRITICAL] shared/utils.ts:45: while ((authorMatch = authorRegex.exec(entry)) !== null) {",
"file_path": "shared/utils.ts"
},
{
"evidence_id": "EV:cisco-6",
"type": "file_excerpt",
"title": "MCP_SQL_BLIND [HIGH] shared/utils.ts:236: await sleep(delay);",
"file_path": "shared/utils.ts"
},
{
"evidence_id": "EV:cisco-7",
"type": "file_excerpt",
"title": "INSTRUCTED_GIT_CLONE_AND_BUILD [MEDIUM] README.md:346: git clone https://github.com/your-username/literature-skills.git",
"file_path": "README.md"
},
{
"evidence_id": "EV:cisco-8",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] paper-viz/scripts/pdf-figure-extractor.ts:182: with open(filepath, \"rb\") as f:",
"file_path": "paper-viz/scripts/pdf-figure-extractor.ts"
},
{
"evidence_id": "EV:cisco-9",
"type": "file_excerpt",
"title": "DATA_EXFIL_BASE64_AND_NETWORK [CRITICAL] paper-viz/scripts/pdf-figure-extractor.ts:183: b64_data = base64.b64encode(f.read()).decode(\"utf-8\")",
"file_path": "paper-viz/scripts/pdf-figure-extractor.ts"
},
{
"evidence_id": "EV:cisco-10",
"type": "file_excerpt",
"title": "MCP_SCRIPT_TAGS [HIGH] paper-viz/scripts/html-generator.ts:48: <script>",
"file_path": "paper-viz/scripts/html-generator.ts"
}
]
}