Back to skill

Security audit

YouCam Clothes Try-On Studio

Security checks for vulnerabilities and agentic risk

Overview

The skill’s photo processing and credit use match its stated purpose, with privacy and dependency precautions to consider.

Selected photos leave your device for YouCam/Perfect Corp processing and consume credits. Use photos you are comfortable sharing, review the provider's privacy terms, and approve the selected steps and total cost. Video prompt enhancement is documented as using Gemini. Protect your API key and use reviewed, patched dependencies. The partial scanner references were resolved through inspection, but live processing, retention behavior, and installed dependency versions were not verified.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
Findings (27)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The skill explicitly excludes skin, hair, and makeup workflows, but its CLI accepts caller-selected features without enforcing that restriction. This creates a scope-enforcement gap that could permit unintended processing and credit spending if an excluded feature's contract is available; the supplied fallback alone contains only the three intended features.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The declared feature boundary is expressed in agent instructions but is not enforced by the generic CLI interface. Excluded operations could therefore become accessible when their contracts are available, although successful execution of those operations is not established by the supplied three-feature fallback.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
requirements:
  credentials:
    - name: YOUCAM_API_KEY
      source: env | credentials.json (in the skill root, next to SKILL.md)
  network:
    - yce-api-01.makeupar.com
  apis:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
worn photo) or a template_id.
2. Run `python scripts/youcam_core.py validate-key` (0 credits) to confirm the key. If it is not set,
   tell the user to get one at <https://yce.perfectcorp.com/api-console> and set the
   `YOUCAM_API_KEY` env var, or create `credentials.json` in the skill root (see
   `credentials.example.json` for the format).

## Flow (only the chosen steps)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/constants.py (reported line 7)May include surrounding context.

python
skills/<skill-name>/
  ├── SKILL.md
  ├── credentials.example.json   # template for credentials.json
  ├── credentials.json           # CREDENTIALS_FILE (user-provided)
  └── scripts/                   # SKILL_SCRIPT_ROOT (this file's folder)
      ├── constants.py, youcam_api.py, ...

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/constants.py (reported line 8)May include surrounding context.

python
skills/<skill-name>/
  ├── SKILL.md
  ├── credentials.example.json   # template for credentials.json
  ├── credentials.json           # CREDENTIALS_FILE (user-provided)
  └── scripts/                   # SKILL_SCRIPT_ROOT (this file's folder)
      ├── constants.py, youcam_api.py, ...
      ├── api-fallback.yaml      # API_FALLBACK_DOC

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/constants.py (reported line 15)May include surrounding context.

python
├── requirements.txt       # REQUIREMENTS_FILE
      └── .venv/                 # VENV_DIR

Every path the scripts use resolves inside `SKILL_SCRIPT_ROOT`, except credentials.json, which lives
one level up in the skill root so users edit it next to SKILL.md rather than inside the vendored code.
"""

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/constants.py (reported line 23)May include surrounding context.

python
SKILL_SCRIPT_ROOT = os.path.dirname(os.path.abspath(__file__))
API_FALLBACK_DOC = os.path.join(SKILL_SCRIPT_ROOT, "api-fallback.yaml")
CREDENTIALS_FILE = os.path.join(os.path.dirname(SKILL_SCRIPT_ROOT), "credentials.json")

# Install dependencies into a local virtual environment in the skill script folder.
VENV_DIR = os.path.join(SKILL_SCRIPT_ROOT, ".venv")

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/youcam_api.py (reported line 90)May include surrounding context.

python
def get_key() -> str:
    """Resolve the API key from the YOUCAM_API_KEY env var or credentials.json.

    Exits with code 2 and a structured error if no usable key is configured.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/youcam_api.py (reported line 108)May include surrounding context.

python
"No API key configured.",
            hint=f'Set the YOUCAM_API_KEY env var, or create {CREDENTIALS_FILE} with {{"api_key": "..."}}'
            + format_hint,
            details="Neither YOUCAM_API_KEY nor credentials.json was found.",
            code=2,
        )

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/youcam_core.py (reported line 9)May include surrounding context.

python
everything the skill needs.

Auth:
    Set the YOUCAM_API_KEY environment variable, or create a credentials.json file (in the
    skill's root, next to SKILL.md) containing {"api_key": "..."}. The env var is used first
    if both are present. If neither is set, the command & API call fails.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/youcam_tasks.py (reported line 123)May include surrounding context.

python
try-on. Follows the same rules as src_file. Not every feature needs this.
        params: Extra options to send along with the request.
        key: The API key to use. Required; the caller (e.g. youcam_core.py's CLI) is
            expected to resolve it from YOUCAM_API_KEY or credentials.json beforehand.
        version: Which version of the feature to call. Defaults to the standard version.
        interval: How many seconds to wait between checks while the job is processing.
        max_polls: How many times to check on the job before giving up and returning

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/youcam_tasks.py (reported line 141)May include surrounding context.

python
contract = contract or load_contract(feature)
    if not key:
        raise ValueError(
            "missing API key. set the YOUCAM_API_KEY env var, or create credentials.json "
            "(see credentials.example.json for the format)"
        )
    body = dict(params or {})

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
using the `task_id` from that output, until `task_status` is `success` or `error`. A task_id
   stays valid for 24 hours.

## Output rules
* **Return the result image/video URL exactly as given** (hyperlink is OK; do not modify or
  shorten it).
* Video can take longer than `run`'s default wait. If it returns `running`, check back with

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, 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 personal photos to a third-party service without explicitly disclosing that transfer.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow submits identifiable personal photos for third-party processing but only requires the agent to obtain choices and acknowledge costs. Naming YouCam in the skill documentation does not ensure users are informed of the photo transfer before it occurs.

Content

No source excerpt is available for this finding.

Prompt enhancement forces English output without user opt-in.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The prompt description accepts any input language but states that enhancement will automatically output English using the Gemini API. No language choice, opt-in, or technical justification for this forced conversion is provided.

Content

No source excerpt is available for this finding.

Tainted flow: 'put_req' from requests.post (line 295, network input) → requests.put (network output)

Medium
Category
Data Flow
Confidence
84% confidence
Finding

The code sends the selected local file to an API-supplied URL without restricting its scheme, destination, or redirects. Although presigned uploads are normal for this service, an attacker who can influence the metadata response could redirect sensitive photo bytes to an unauthorized destination or cause requests to internal services; response control is a prerequisite, not demonstrated here.

Content

Scanner excerpt · scripts/youcam_api.py (reported line 297)May include surrounding context.

python
info = meta.json()["data"]["files"][0]
    put_req = info["requests"][0]
    with open(file_path, "rb") as fh:
        requests.put(
            put_req["url"],
            headers=put_req.get("headers", {"Content-Type": ct}),
            data=fh,

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/youcam_api.py (reported line 313)May include surrounding context.

python
Args:
        contract: The feature's loaded API contract, e.g. from load_contract().
        feature: Which YouCam feature to create a task for, e.g. "skin-analysis".
        body: The request payload, e.g. file_id(s)/url(s) and any feature-specific params.
        key: The API key to authenticate the request with.
        version: Which version of the feature to call. Defaults to the standard version.

The CLI exposes arbitrary YouCam features rather than restricting execution to clothes try-on, background changes, and motion generation.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The run branch passes the caller's feature directly into contract loading and execution without a skill-specific allowlist. This fails to enforce the clothing skill's stated limits and could enable unintended billable or sensitive-photo operations when additional contracts are available; actual support for excluded features depends on the unprovided loader.

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/youcam_init.py (reported line 49)May include surrounding context.

python
def _run_setup_step(cmd: list[str]) -> None:
    """Run one setup command, exiting with a structured error if it fails."""
    try:
        subprocess.run(cmd, check=True)
    except subprocess.CalledProcessError as exc:
        exit_with_error(
            "setup_failed",

The task runner exposes arbitrary YouCam features despite the manifest limiting the skill to clothes try-on, background changes, and motion video.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The caller-controlled feature is passed to load_contract(), create_task(), and poll() without checking whether it belongs to the declared workflow. This is a general-purpose feature runner: its documentation explicitly advertises skin analysis (L112) and hair transfer (L118-L120), both outside the manifest's scope and explicitly excluded from skill use.

Content

No source excerpt is available for this finding.

The mandatory closing disclaimer requires English output without a language choice.

Low
Category
Output Handling
Confidence
85% confidence
Finding

The skill requires every response to end with a fixed English disclaimer, including when the user communicates in another language. It provides neither a localization option nor a justification for requiring that language.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The open-ended requests constraint permits installations to change without review, undermining reproducibility and dependency integrity. This is a supply-chain weakness rather than evidence that a malicious or vulnerable release is currently installed.

Content

Scanner excerpt · scripts/requirements.txt (reported line 1)May include surrounding context.

text
requests>=2.28
PyYAML>=6.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
88% confidence
Finding

requests>=2.28 permits releases affected by newer Requests advisories, including credential-disclosure issues. This is an insufficient minimum-version constraint, not proof that the installed release is vulnerable or that every listed historical advisory applies.

Content

No source excerpt is available for this finding.