Back to skill

Security audit

instagram-skill

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the Instagram work it describes and requires approval before posting, though its fallback login and validation checks need care.

Use browser sign-in when available, and keep API-key URLs and upload-session files private. Connect only intended accounts and review the complete preview before approving publication. Run the media checker again without --fix after repairs, and verify CSV measurement dates before relying on rankings. The remote service and client credential storage were not audited.

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 (21)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

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

Content

Scanner excerpt · scripts/render_slides.py (reported line 140)May include surrounding context.

python
return "#" + v.upper()


def mix(a, b, t):
    a, b = a.lstrip("#"), b.lstrip("#")
    ca = [int(a[i:i + 2], 16) for i in (0, 2, 4)]
    cb = [int(b[i:i + 2], 16) for i in (0, 2, 4)]
    return "#" + "".join(f"{round(x + (y - x) * t):02X}" for x, y in zip(ca, cb))


# ---------- rich text ----------

TOKEN = re.compile(r"(~~.+?~~|\*[^*]+?\*)")
EMOJI = re.compile("[\U0001F000-\U0001FAFF☀-➿️‍]")


def runs(text):
    """Split markup into words. Each word is a list of (text, accent, strike) pieces, so
    punctuation right after *accent* stays attached ("*twice*." renders as "twice.").
    A "\\n" word marks a line break."""
    text = str(text or "")
    if EMOJI.search(text):
        warn("emoji removed from slide text (the bundled fonts have no emoji); put emoji in the caption")
        text = re.sub(r" {2,}", " ", EMOJI.sub("", text)).strip()
    text = smart_quotes(text)
    out = []
    prev_tail_space = True
    for part in TOKEN.split(text):
        if not part:

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: 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.

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 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 28)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
98% confidence
Finding

The fallback instructs users to embed an API credential in a URL query string, which can expose it through configuration files, command history, diagnostic output, and request logs even over HTTPS. Anyone obtaining the key could exercise its granted posting or account-management permissions; the warning against sharing keys does not prevent these incidental disclosures.

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 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.

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
returns a link; the user opens it, approves, and tells you when they're done. Confirm with
`social_accounts_list`. Repeat per platform.

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

## 3. Upload the media

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")
PIP = "py -m pip" if system == "Windows" else "python3 -m pip"
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 41)May include surrounding context.

python
line("missing", "Pillow", f"{PIP} install pillow")

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:
    line("needed for video", "ffmpeg", f"{INSTALL_FFMPEG}  (photos and carousels work without it)")

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/ig_check.py (reported line 59)May include surrounding context.

python
def probe_video(path):
    if not shutil.which("ffprobe"):
        sys.exit("ffprobe not found: install ffmpeg to check videos (see scripts/check_setup.py)")
    out = subprocess.run(["ffprobe", "-v", "error", "-show_format", "-show_streams", "-of", "json", path],
                         capture_output=True, text=True)
    if out.returncode != 0:
        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/ig_check.py (reported line 284)May include surrounding context.

python
def edge_colour(src):
    """The average colour of the video's top and bottom edges, so the plate blends into it."""
    tmp = src + ".edge.png"
    subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", "1", "-i", src, "-frames:v", "1", "-vf", "scale=64:-2", tmp],
                   capture_output=True)
    try:
        with Image.open(tmp) as im:

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/ig_check.py (reported line 352)May include surrounding context.

python
"-crf", "19", "-maxrate", "20M", "-bufsize", "40M", "-color_primaries", "bt709", "-color_trc", "bt709",
               "-colorspace", "bt709", "-c:a", "aac", "-b:a", "192k", "-ar", "48000", "-ac", "2",
               "-movflags", "+faststart", dst]
        r = subprocess.run(cmd, capture_output=True, text=True)
        os.remove(plate)
        if r.returncode != 0:
            raise RuntimeError(r.stderr.strip().splitlines()[-1] if r.stderr.strip() else "ffmpeg failed")

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/ig_check.py (reported line 371)May include surrounding context.

python
"-maxrate", "20M", "-bufsize", "40M", "-color_primaries", "bt709", "-color_trc", "bt709",
           "-colorspace", "bt709", "-c:a", "aac", "-b:a", "192k", "-ar", "48000", "-ac", "2",
           "-movflags", "+faststart", dst]
    r = subprocess.run(cmd, capture_output=True, text=True)
    if r.returncode != 0:
        raise RuntimeError(r.stderr.strip().splitlines()[-1] if r.stderr.strip() else "ffmpeg failed")
    return dst

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/ig_check.py (reported line 391)May include surrounding context.

python
def has_zscale():
    global _zs
    if _zs is None:
        out = subprocess.run(["ffmpeg", "-hide_banner", "-filters"], capture_output=True, text=True).stdout
        _zs = " zscale " in out
    return _zs

The --fix workflow can report success without verifying that repaired media satisfies the documented limits.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

Successful conversion is counted as a fix without checking the resulting media, and --fix can exit successfully while unresolved fix-level issues remain. This weakens the validation gate and can mislead the agent into uploading invalid media, although the later provider-validation step limits the likely impact to workflow failures.

Content

No source excerpt is available for this finding.

CSV analytics bypass the promised measurement-age safeguards and can be assigned a fabricated day-seven age.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

CSV values overwrite stored measurements without enforcing the promised age window, and missing publication timestamps cause those values to receive an invented age of seven days. Averaging metric ages can also conceal an out-of-window measurement, allowing malformed or manipulated imports to poison rankings and posting advice rather than compromise the host.

Content

No source excerpt is available for this finding.

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/preview.py (reported line 45)May include surrounding context.

python
if not shutil.which("ffmpeg"):
            img = Image.new("RGB", (540, 960), "#222")
        else:
            subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", "1", "-i", src, "-frames:v", "1",
                            "-vf", "scale=540:-2", dst], capture_output=True)
            img = Image.open(dst).convert("RGB") if os.path.exists(dst) else Image.new("RGB", (540, 960), "#222")
    else:

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/reel.py (reported line 37)May include surrounding context.

python
def duration(path):
    out = subprocess.run(["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "json", path],
                         capture_output=True, text=True).stdout
    try:
        return float(json.loads(out)["format"]["duration"])

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/reel.py (reported line 48)May include surrounding context.

python
def grab(path, t, out):
    """One frame at time t, scaled and cropped to fill 1080x1920 the way a 9:16 Reel shows."""
    vf = f"scale={W}:{H}:force_original_aspect_ratio=increase,crop={W}:{H}"
    r = subprocess.run(["ffmpeg", "-y", "-v", "error", "-ss", f"{t:.3f}", "-i", path, "-frames:v", "1",
                        "-vf", vf, "-q:v", "2", out], capture_output=True, text=True)
    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/render_slides.py (reported line 96)May include surrounding context.

python
urllib.request.urlretrieve(url, path)
    except Exception:
        if shutil.which("curl"):
            subprocess.run(["curl", "-sfL", url, "-o", path], check=False)
    if not os.path.exists(path) or os.path.getsize(path) < 10000:
        sys.exit(f"Font {name} missing and could not be downloaded from {url}")
    return path

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 28)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)