Back to skill

Security audit

YouTube Skill

Security checks for vulnerabilities and agentic risk

Overview

This YouTube helper needs review because it transfers video before the promised approval and has a conditional flaw that could upload an unintended local file.

Require approval before any video transfer to WoopSocial and its Cloudflare storage, separately from publication approval. Prefer OAuth over API keys in connection URLs. For private media, select --engine local or existing captions explicitly; automatic selection uses available cloud transcription keys. Before cloud transcription, fix the curl fallback to treat text fields literally and validate language codes. This review verified bundled behavior, not remote service permissions or retention.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (33)

Tainted flow: 'req' from os.environ.get (line 41, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/suggest.py (reported line 42)May include surrounding context.

python
except ImportError:
            pass
        req = urllib.request.Request(url, headers=UA)
        with urllib.request.urlopen(req, timeout=timeout, context=ctx) as r:
            return r.read()
    except urllib.error.HTTPError:
        raise

Tainted flow: 'req' from os.environ.get (line 99, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/transcribe.py (reported line 102)May include surrounding context.

python
req = urllib.request.Request(url, data=bytes(body), method="POST", headers={
        "Authorization": f"Bearer {key}", "Content-Type": f"multipart/form-data; boundary={boundary}"})
    try:
        with urllib.request.urlopen(req, timeout=600) as r:
            return json.loads(r.read())
    except urllib.error.HTTPError as e:
        sys.exit(f"Transcription API error {e.code}: {e.read().decode(errors='replace')[:400]}")

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.

md
1. `social_accounts_list`; not connected: the one connect path for this agent (free plan: 2
   social accounts), then `oauth_create_authorization` for YouTube.
2. Upload the video with an upload session (`media_uploads_create_session` with `bytes` from
   `pack/manifest.json`, `python3 scripts/upload_parts.py session.json final.mp4`,
   `media_uploads_complete_session`).
3. Fill the IDs into `pack/post.json` and run `posts_validate`.

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · scripts/upload_parts.py (reported line 2)May include surrounding context.

python
#!/usr/bin/env python3
"""Upload one file to a WoopSocial media upload session (standard library only).

WoopSocial uploads work in three steps:
  1. The agent calls `media_uploads_create_session` with the projectId and the file size in bytes.

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · scripts/upload_parts.py (reported line 63)May include surrounding context.

python
except urllib.error.HTTPError as err:
            if err.code == 403:
                sys.exit(f"Part {n} was refused (HTTP 403): the upload links have probably expired. "
                         "Create a new upload session and run this again.")
            problem = f"HTTP {err.code}: {err.reason}"
        except (urllib.error.URLError, OSError, RuntimeError, subprocess.TimeoutExpired) as err:
            problem = str(getattr(err, "reason", err))

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, mcp, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The workflow sends the video to WoopSocial before approval without warning the user that this transfer precedes confirmation.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow transfers the complete video to WoopSocial-controlled storage before requesting the user's clear approval. Although publication requires confirmation, that confirmation cannot undo disclosure of an unpublished or sensitive video to a third-party service, and the workflow does not explicitly obtain consent for this earlier transfer.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/woopsocial.md (reported line 27)May include surrounding context.

md
|---|---|
| Claude (claude.ai, Desktop, Cowork) | Add WoopSocial from the [Claude directory](https://claude.ai/directory/woopsocial), click Connect and sign in |
| Cursor | Install from [cursor.directory](https://cursor.directory/plugins/woopsocial-social-media-scheduler) and sign in |
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/woopsocial.md (reported line 28)May include surrounding context.

md
| Claude (claude.ai, Desktop, Cowork) | Add WoopSocial from the [Claude directory](https://claude.ai/directory/woopsocial), click Connect and sign in |
| Cursor | Install from [cursor.directory](https://cursor.directory/plugins/woopsocial-social-media-scheduler) and sign in |
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The fallback instructs users to place a password-equivalent API key in the MCP URL query string. Such URLs can be retained in client configuration, diagnostic output, access logs, or copied setup commands, exposing the credential despite HTTPS and the accompanying warning not to share it.

Content

Scanner excerpt · references/woopsocial.md (reported line 30)May include surrounding context.

md
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

The API key is a password: never paste it into shared chats or commit it.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/woopsocial.md (reported line 39)May include surrounding context.

md
the user opens it, picks the channel, approves, and tells you when they're done. Confirm with
`social_accounts_list`.

Find IDs yourself with `projects_list` and `social_accounts_list`; never ask the user to paste
IDs.

## 3. Upload the video

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/check_setup.py (reported line 13)May include surrounding context.

python
system = platform.system()
INSTALL_FFMPEG = {"Darwin": "brew install ffmpeg", "Windows": "winget install ffmpeg",
                  "Linux": "sudo apt install ffmpeg   (or your distro's package manager)"}.get(system, "install ffmpeg")
ok = True

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/check_setup.py (reported line 28)May include surrounding context.

python
line("ok", "Python", platform.python_version())

if shutil.which("ffmpeg") and shutil.which("ffprobe"):
    v = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True).stdout.split("\n")[0]
    line("ok", "ffmpeg", v.replace("ffmpeg version ", "")[:60])
else:
    ok = False

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/suggest.py (reported line 49)May include surrounding context.

python
except Exception as e:
        if "CERTIFICATE" not in str(e).upper() or not shutil.which("curl"):
            raise
        out = subprocess.run(["curl", "-sS", "-m", str(timeout), "-A", UA["User-Agent"], url],
                             capture_output=True)
        if out.returncode:
            raise RuntimeError(out.stderr.decode(errors="replace").strip())

Tainted flow: 'url' from os.environ.get (line 57, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/suggest.py (reported line 49)May include surrounding context.

python
except Exception as e:
        if "CERTIFICATE" not in str(e).upper() or not shutil.which("curl"):
            raise
        out = subprocess.run(["curl", "-sS", "-m", str(timeout), "-A", UA["User-Agent"], url],
                             capture_output=True)
        if out.returncode:
            raise RuntimeError(out.stderr.decode(errors="replace").strip())

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 95)May include surrounding context.

python
def video_duration(path):
    out = subprocess.run(["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of",
                          "default=nw=1:nk=1", path], capture_output=True, text=True).stdout.strip()
    try:
        return float(out)

Tainted flow: 'path' from open (line 464, file read) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 95)May include surrounding context.

python
def video_duration(path):
    out = subprocess.run(["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of",
                          "default=nw=1:nk=1", path], capture_output=True, text=True).stdout.strip()
    try:
        return float(out)

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 110)May include surrounding context.

python
best = None
    start = max(0.0, t - 0.25)
    pattern = os.path.join(tmp, f"g{int(t * 1000)}_%02d.png")
    subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", f"{start:.3f}", "-i", video, "-t", "0.5",
                    "-vf", "fps=10", "-frames:v", "6", pattern], check=True)
    for k in range(1, 7):
        p = pattern % k

Tainted flow: 'video' from open (line 207, file read) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 110)May include surrounding context.

python
best = None
    start = max(0.0, t - 0.25)
    pattern = os.path.join(tmp, f"g{int(t * 1000)}_%02d.png")
    subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", f"{start:.3f}", "-i", video, "-t", "0.5",
                    "-vf", "fps=10", "-frames:v", "6", pattern], check=True)
    for k in range(1, 7):
        p = pattern % k

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 434)May include surrounding context.

python
short, vertical = 720, False
    if spec.get("video"):
        v = spec["video"] if os.path.isabs(spec["video"]) else os.path.join(base, spec["video"])
        out = subprocess.run(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries",
                              "stream=width,height:stream_side_data=rotation", "-of", "csv=p=0", v],
                             capture_output=True, text=True).stdout
        try:

Tainted flow: 'v' from open (line 433, file read) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/thumbnail.py (reported line 434)May include surrounding context.

python
short, vertical = 720, False
    if spec.get("video"):
        v = spec["video"] if os.path.isabs(spec["video"]) else os.path.join(base, spec["video"])
        out = subprocess.run(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries",
                              "stream=width,height:stream_side_data=rotation", "-of", "csv=p=0", v],
                             capture_output=True, text=True).stdout
        try:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/transcribe.py (reported line 29)May include surrounding context.

python
# Captions for a published video leave fillers out, so the prompt only carries names and terms.

API = {
    "groq": ("https://api.groq.com/openai/v1/audio/transcriptions", "GROQ_API_KEY", "whisper-large-v3-turbo"),
    "openai": ("https://api.openai.com/v1/audio/transcriptions", "OPENAI_API_KEY", "whisper-1"),
}
API_LIMIT = 24 * 1024 * 1024  # both APIs refuse files over 25 MB

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/transcribe.py (reported line 30)May include surrounding context.

python
API = {
    "groq": ("https://api.groq.com/openai/v1/audio/transcriptions", "GROQ_API_KEY", "whisper-large-v3-turbo"),
    "openai": ("https://api.openai.com/v1/audio/transcriptions", "OPENAI_API_KEY", "whisper-1"),
}
API_LIMIT = 24 * 1024 * 1024  # both APIs refuse files over 25 MB
CHUNK_SECONDS = 20 * 60

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/transcribe.py (reported line 39)May include surrounding context.

python
def need_ffmpeg():
    if not shutil.which("ffmpeg") or not shutil.which("ffprobe"):
        sys.exit("ffmpeg is not installed. Mac: brew install ffmpeg. Windows: winget install ffmpeg. "
                 "Linux: sudo apt install ffmpeg (or your distro's package).")


def duration(path):

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/youtube_pack.py (reported line 66)May include surrounding context.

python
def need_ffmpeg():
    if not shutil.which("ffmpeg") or not shutil.which("ffprobe"):
        sys.exit("ffmpeg is not installed. Mac: brew install ffmpeg. Windows: winget install ffmpeg. "
                 "Linux: sudo apt install ffmpeg (or your distro's package).")


def probe(path):