Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent pet-media analysis wrapper, but it silently creates/reuses user identities, provisions backend login tokens, stores them locally, and queries cloud report history with limited user control.
Install only if you are comfortable with pet images/videos or URLs being sent to lifeemergence.com services, a hidden local user identity being created or reused, backend login/session tokens being stored in the workspace SQLite database, and prior cloud reports being queryable through the skill. Prefer running it in a constrained workspace and review the provider's privacy and retention terms first.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
The skill appears to perform authenticated outbound API access, local file operations, environment inspection, open-id generation/persistence, database-backed token lookup, and automatic account/login provisioning via an external endpoint, none of which are central to the declared pet-drying purpose. In combination, these hidden identity and network features create a substantial privacy and account-abuse surface.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
---
name: "smyx-adaptive-pet-drying-temperature-analysis"
description: "Triggers when a user provides a full-body image/video of a pet (multi-angle preferred) for analysis; supports local uploads or network URLs to call server-side APIs for breed/body-type recognition and fur-density estimation (sparse / medium / dense), then outputs a recommended drying temperature curve (temperature in ℃ + time in minutes) for personalized care to reduce scald risk (not a medical recommendation). Application scenarios: pet drying boxes, pet grooming salons, smart pet care devices. | 当用户提供宠物全身图像/视频（多角度最佳）时，触发本技�
This module can synthesize, persist, and reuse default user identities when none are supplied, including writing user records to local storage. For a pet drying skill, silent identity generation is unnecessary and dangerous because it enables opaque tracking, implicit account creation, and backend actions attributed to users who never explicitly authenticated.
The utility layer performs account bootstrap, token acquisition, token persistence, and user lookup that are unrelated to pet drying temperature analysis. This expands the skill from image analysis into hidden identity and authentication management, enabling silent enrollment and credential handling against backend services without clear necessity or user consent.
The skill advertises and instructs use of shell, network, file read/write, and environment-backed behavior but declares no explicit tool scope or permission boundaries. In an agent environment, this increases the chance of over-privileged execution, making it easier for the skill to access local files, invoke commands, and send data off-box without clear policy enforcement.
The top-level behavior statement suggests only current-media analysis, while the body also defines built-in historical report retrieval and report-link output. This under-disclosure can mislead users and reviewers about what data is accessed and what persistent/report-sharing features are active.
The skill mentions network URLs and server-side/cloud API processing without an explicit privacy or data-transmission warning. Users may not realize their media or referenced content is sent to remote services, which is especially sensitive for uploaded pet videos/images that may include household or location details.
The default trigger condition is broad enough to activate on essentially any pet image/video submission, which can cause the skill to process media unexpectedly. When combined with network APIs and local saving, overbroad triggering increases the chance of unintentional data transfer and analysis without clear user intent.
Automatic cloud-based historical report lookup and persistent user/report association extend the skill beyond one-time pet-media analysis into ongoing user data management. This broadens the privacy footprint and can expose prior reports without users realizing the skill maintains and queries account-linked history.
The skill states that uploaded attachments or media files are automatically saved locally, but it does not provide a clear user-facing warning or retention explanation. Local persistence of user media introduces privacy and potential filesystem risk, especially for images/videos that may contain incidental sensitive content or metadata.
This code defines the command description and multiple help strings entirely in Chinese, and later prints Chinese-only status/error messages. That forces a specific language/locale on all users without offering an alternative or opt-in, which matches the language-policy violation criteria.
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)
result_json_common_ai_response = result_json.get("commonAiResponse") if isinstance(result_json,
dict) else result_json
if result_json_common_ai_response:
result_json = result_json_common_ai_response
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)
result_json_common_ai_response = result_json.get("commonAiResponse") if isinstance(result_json,
dict) else result_json
if result_json_common_ai_response:
result_json = result_json_common_ai_response
The user-facing output is labeled as a generic structured analysis report and includes a report export image link, while the manifest promises breed recognition, fur-density estimation, and a recommended drying temperature curve in ℃ and minutes. Nothing in this file formats or verifies those pet-specific outputs, so the implemented behavior here is broader and more generic than the declared purpose.
Detected: suspicious.install_untrusted_source