๐Ÿ›ก๏ธ SafeAgentSkills

Browser Audio Capture

ยท v1.1.0

High Risk

Capture audio from any browser tab โ€” meetings, YouTube, podcasts, courses, webinars โ€” and stream to any AI agent. Zero API keys, works with any framework.

H:4 D:4 A:3 C:1

โš ๏ธ Hazard Flags

FS_READ_USER NET_EGRESS_ANY CREDS_BROWSER ACT_SEND_MESSAGE PI_WEB

๐Ÿ“‹ Capabilities

Execution

  • โŒ Shell execution
  • โŒ Code execution
  • โŒ Install dependencies
  • โŒ Persistence
  • Privilege: user

Filesystem

  • โŒ Read workspace
  • โŒ Write workspace
  • โœ… Read home
  • โŒ Write home
  • โŒ Read system
  • โŒ Delete

Network

  • Egress: any
  • โŒ Ingress

Credentials

  • โŒ Environment vars
  • โŒ Credential files
  • โœ… Browser data
  • โŒ Keychain

Actions

โœ… send messagesโŒ post publicโŒ purchaseโŒ transfer moneyโŒ deployโŒ delete external

๐Ÿ”’ Containment

Level: maximum

Required:
  • APPROVE_SEND: Can send messages
Recommended:
  • LOG_ACTIONS: Audit trail for all actions

โšก Risks

Code obfuscation detected in: scripts/browser_capture/audio_capture.py, scripts/extension/offscreen.js medium

Mitigation: Deobfuscate and review code before use.

Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP high

Mitigation: Add proper exit conditions or limits to loops

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL high

Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments

Command injection risk: MCP_SQL_BLIND high

Mitigation: Remove SQL exploitation patterns.

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS medium

Mitigation: Ensure network access is necessary and documented

Want a deeper analysis?

This report was generated by static analysis. Get an LLM-powered deep review with behavioral reasoning and attack surface mapping.

๐Ÿง  Deep Analysis โ€” $5.00

๐Ÿšจ Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

๐Ÿ“„ Raw SSDS JSON click to expand
{
  "meta": {
    "document_id": "ssds:auto:browser-audio-capture:1.1.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:32:11.736Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Browser Audio Capture",
    "version": "1.1.0",
    "format": "agent_skill",
    "description": "Capture audio from any browser tab โ€” meetings, YouTube, podcasts, courses, webinars โ€” and stream to any AI agent. Zero API keys, works with any framework.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "0e3e7eae0930d378645dbc93db83bd906336943506ebe3b81827e3619bb0dff3",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": false,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": false,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "writes_system": false,
      "can_delete": false
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": false,
      "reads_credential_files": false,
      "reads_browser_data": true,
      "reads_keychain": false
    },
    "services": [],
    "actions": {
      "can_send_messages": true,
      "can_post_public": false,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "FS_READ_USER",
      "NET_EGRESS_ANY",
      "CREDS_BROWSER",
      "ACT_SEND_MESSAGE",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "CRED_BROWSER",
        "name": "Browser Profile Access",
        "description": "Accesses browser cookies/profiles in: SKILL.md"
      },
      {
        "code": "OBFUSCATED_CODE",
        "name": "Obfuscated Code",
        "description": "Contains obfuscated code patterns in: scripts/browser_capture/audio_capture.py, scripts/extension/offscreen.js"
      },
      {
        "code": "RESOURCE_ABUSE",
        "name": "Resource Abuse Risk",
        "description": "RESOURCE_ABUSE_INFINITE_LOOP detected: Infinite loop without clear exit condition"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL: Instructs agent to install external binary or package"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "MCP_SQL_BLIND: Blind SQL injection, system table access, or stored procedure abuse"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 7 security patterns (7 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_SEND",
        "reason": "Can send messages"
      }
    ],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "risk": "Code obfuscation detected in: scripts/browser_capture/audio_capture.py, scripts/extension/offscreen.js",
        "severity": "medium",
        "mitigation": "Deobfuscate and review code before use."
      },
      {
        "risk": "Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP",
        "severity": "high",
        "mitigation": "Add proper exit conditions or limits to loops"
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL",
        "severity": "high",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND",
        "severity": "high",
        "mitigation": "Remove SQL exploitation patterns."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS",
        "severity": "medium",
        "mitigation": "Ensure network access is necessary and documented"
      }
    ],
    "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": "scripts/browser_capture/__init__.py",
      "file_path": "scripts/browser_capture/__init__.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/browser_capture/audio_capture.py",
      "file_path": "scripts/browser_capture/audio_capture.py"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/browser_capture/cdp_client.py",
      "file_path": "scripts/browser_capture/cdp_client.py"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/browser_capture/cli.py",
      "file_path": "scripts/browser_capture/cli.py"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/extension/background.js",
      "file_path": "scripts/extension/background.js"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/extension/manifest.json",
      "file_path": "scripts/extension/manifest.json"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "scripts/extension/offscreen.js",
      "file_path": "scripts/extension/offscreen.js"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "scripts/extension/popup.js",
      "file_path": "scripts/extension/popup.js"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/extension/README.md",
      "file_path": "scripts/extension/README.md"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/browser_capture/audio_capture.py:23: import aiohttp",
      "file_path": "scripts/browser_capture/audio_capture.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "RESOURCE_ABUSE_INFINITE_LOOP [HIGH] scripts/browser_capture/audio_capture.py:308: while True:",
      "file_path": "scripts/browser_capture/audio_capture.py"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] scripts/browser_capture/audio_capture.py:334: await asyncio.sleep(check_interval)",
      "file_path": "scripts/browser_capture/audio_capture.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/browser_capture/cdp_client.py:5: import aiohttp",
      "file_path": "scripts/browser_capture/cdp_client.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] scripts/extension/manifest.json:1: {",
      "file_path": "scripts/extension/manifest.json"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:29: Python 3.9+ with aiohttp: `pip install aiohttp`",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}