Back to skill

Security audit

cross-post-video-skill

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious with medium confidence, chiefly because it documents using an API key in an MCP URL, which can expose the key through saved configuration or logs.

Review the API-key setup instructions before installing, and avoid placing a key in a URL that may be saved or logged. The scan inspected all listed components but was marked partial because some local references could not be resolved, so the evidence is incomplete.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (18)

YARA rule 'privilege_escalation_tools': Privilege escalation tools and techniques [hacktools]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · examples/microgravity/plan.html (reported line 24)May include surrounding context.

html
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

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.

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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · SKILL.md (reported line 295)May include surrounding context.

md
a gap between platforms, a posting time or a hashtag count changes how a video is distributed,
  and #Shorts isn't needed. Say what is true: the checks catch what can be known before upload,
  and the texts fit each platform.
- Copy an @handle from one platform's text to another's without asking.

## Files

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 37)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 restart with `claude --continue` (keeps the conversation), `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial`, then start a new session (`codex resume --last` keeps this one) |
| 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_k=

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 38)May include surrounding context.

md
(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 restart with `claude --continue` (keeps the conversation), `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial`, then start a new session (`codex resume --last` keeps this one) |
| 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 an API key in the MCP URL query string. Such URLs can be retained in client configuration, diagnostic output and infrastructure access logs, potentially exposing credentials that authorize posting actions; HTTPS and the warning against sharing keys do not prevent those exposures.

Content

Scanner excerpt · references/woopsocial.md (reported line 40)May include surrounding context.

md
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then restart with `claude --continue` (keeps the conversation), `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial`, then start a new session (`codex resume --last` keeps this one) |
| 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. Claude Code and Codex
load new tools only in a new session, and a restart stops a running script: never add the

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 58)May include surrounding context.

md
**Connect every account in one pass.** Find the project with `projects_list`, then call
`oauth_create_authorization` for each platform that is missing and give the user all the links in
one message. When they say they're done, call `social_accounts_list` once and put each
`socialAccountId` in `crosspost.json`. If a link has expired, make a new one. Never ask the user to
paste IDs.

## 3. Read each account's limits

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 27)May include surrounding context.

python
else:
        line("ok", "Python", platform.python_version())
    if shutil.which("ffmpeg") and shutil.which("ffprobe"):
        out = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True).stdout.split("\n")[0]
        line("ok", "ffmpeg", (out.split() + ["", "", "?"])[2] + ": reads the video and re-encodes it when needed")
        if not any(xplib.ffmpeg_has("encoders", e) for e in ("libx264", "h264_videotoolbox", "h264_mf",
                                                               "h264_nvenc", "h264_qsv", "libopenh264")):

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 40)May include surrounding context.

python
"an ffmpeg build with zscale")
    else:
        line("missing", "ffmpeg", "Mac: brew install ffmpeg. Windows: winget install Gyan.FFmpeg (then open a "
             "new terminal). Linux: sudo apt install ffmpeg")
        ok = False
    try:
        import PIL

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_video.py (reported line 120)May include surrounding context.

python
encode(encoder(int(cap * 0.9), exact=True))
        if os.path.getsize(part) > SIZE_TARGET:
            die("the re-encoded file is still over Instagram's 300 MB; nothing was written. Post a shorter cut there")
        r = subprocess.run(["ffmpeg", "-v", "error", "-i", part, "-f", "null", "-"], capture_output=True, text=True,
                           encoding="utf-8", errors="replace")
        if r.returncode != 0 or r.stderr.strip():
            die("the new file didn't play back cleanly; nothing was written. ffmpeg said: "

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/cover.py (reported line 41)May include surrounding context.

python
def frame(video, t, tmp, k):
    out = os.path.join(tmp, f"f{k}.jpg")
    r = subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", f"{t:.3f}", "-i", video, "-frames:v", "1",
                        "-q:v", "2", out], capture_output=True, text=True, encoding="utf-8", errors="replace")
    if r.returncode != 0 or not os.path.exists(out):
        return None

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/upload_parts.py (reported line 40)May include surrounding context.

python
def put_with_curl(url, chunk):
    """Fallback for Python builds without system certificates (common on macOS)."""
    result = subprocess.run(
        ["curl", "-fsS", "-X", "PUT", "-H", "Content-Type: application/octet-stream",
         "--data-binary", "@-", "-o", os.devnull, "-w", "%{http_code}", url],
        input=chunk, capture_output=True, timeout=300)

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/xplib.py (reported line 160)May include surrounding context.

python
import shutil
    if not (shutil.which("ffmpeg") and shutil.which("ffprobe")):
        die("ffmpeg not found. Mac: brew install ffmpeg. Windows: winget install Gyan.FFmpeg (then open a "
            "new terminal). Linux: sudo apt install ffmpeg")


def run(cmd):

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/xplib.py (reported line 164)May include surrounding context.

python
def run(cmd):
    r = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace")
    if r.returncode != 0:
        last = (r.stderr.strip().splitlines() or ["(it gave no message)"])[-1].strip()
        die(f"{os.path.basename(cmd[0])} could not finish: {last}")

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/xplib.py (reported line 174)May include surrounding context.

python
@functools.lru_cache(maxsize=None)
def ffmpeg_has(kind, name):
    """Whether this ffmpeg build has an encoder or filter."""
    r = subprocess.run(["ffmpeg", "-hide_banner", f"-{kind}"], capture_output=True, text=True,
                       encoding="utf-8", errors="replace")
    return bool(re.search(rf"\s{re.escape(name)}\s", r.stdout))

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/xplib.py (reported line 272)May include surrounding context.

python
def _measured_duration(path, fps):
    """Length of a file that doesn't store one (browser and screen recordings): from its frames."""
    r = subprocess.run(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries", "packet=pts_time",
                        "-of", "csv=p=0", path], capture_output=True, text=True, encoding="utf-8", errors="replace")
    times = []
    for x in r.stdout.replace(",", " ").split():

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/xplib.py (reported line 296)May include surrounding context.

python
if not os.path.getsize(path):
        die(f"{name} is an empty file (0 bytes)")
    need_ffmpeg()
    r = subprocess.run(["ffprobe", "-v", "error", "-show_streams", "-show_format", "-of", "json", path],
                       capture_output=True, text=True, encoding="utf-8", errors="replace")
    try:
        d = json.loads(r.stdout or "{}")