Back to skill

Security audit

Outdoor Sports Event Risk Analysis Tool | 户外体育赛事风险分析工具

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report undisclosed remote identity and video processing, behavior that may exceed the stated sports-safety purpose, and gaps in the analysis workflow.

Consider not installing until the publisher explains the remote processing and account behavior, documents what information is sent and where it is stored, and clarifies whether export-only mode avoids analysis. The scan was partial: one local reference could not be resolved, so the evidence does not cover that reference.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (21)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code is a generic, nonfunctional agent-integration scaffold rather than an implementation of the declared sports-safety analyzer. It does not execute an external command or visibly analyze video. Imported base classes and API services may provide additional functionality, but their implementations are not supplied and cannot substantiate the declared capabilities. No malicious or unrelated resource access is demonstrated.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The workflow mandates silent creation and reuse of a persistent default identity without a user-facing account notice or an explicit user-binding requirement. In a shared deployment, this can associate different users' sensitive sports-health reports with the same default identity; however, remote registration flags, credential persistence, and payment-skill instructions are not established by this source.

Content

No source excerpt is available for this finding.

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 · SKILL.md (reported line 3)May include surrounding context.

md
---
name: "sport-analysis"
description: "Conducts video safety risk analysis for participants in outdoor sports competitions, long-distance running, marathons, etc.; identifies sports injuries and sudden health risks, outputs professional analysis reports, and provides timely warnings to ensure sports safety. | 户外体育赛事风险分析工具,针对户外体育比赛、长跑马拉松等运动项目的参赛人员进行视频安全风险分析,识别运动损伤和突发健康风险,输出专业分析报告,及时预警保障运动安全"
version: "1.0.25"
license: "MIT-0"
---

# 🏃 Outdoor Sports Event R

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, 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 analysis workflow lacks a privacy warning about remote processing of participant footage and cloud-accessible reports.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

Although cloud queries and API use are mentioned, the workflow does not clearly warn that local participant footage leaves the device or explain report storage and access. Identifiable footage and inferred injury or health information make this omission more consequential than ordinary media processing.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to analyze, but analysis still executes.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser accepts --export-env-only and promises not to analyze, but execution never checks the flag. When an input is supplied, the normal analysis path still runs, potentially submitting sensitive footage or consuming paid resources despite the explicit no-analysis request.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

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.

Content

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

python
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

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

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.

Content

Scanner excerpt · skills/smyx_analysis/scripts/skill.py (reported line 33)May include surrounding context.

python
result_json = result_json_common_ai_response

        result_json_health_ai_response = result_json.get("healthAiResponse") if isinstance(result_json,
                                                                                           dict) else result_json
        if result_json_health_ai_response:
            result_json = result_json_health_ai_response

Local input files are submitted to an analysis API without disclosing the upload.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The local-file branch reads the entire selected file and passes its bytes to the analysis API without a disclosure or consent gate in this path. Participant footage can identify individuals and reveal health conditions, so submitting it remotely without informed authorization creates a meaningful privacy risk.

Content

No source excerpt is available for this finding.

The documented export-only mode still executes video analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The export-only flag is parsed but never consulted before identity initialization and video analysis. Supplying the flag alongside a video therefore does not prevent processing, creating a risk of unintended remote disclosure or service charges.

Content

No source excerpt is available for this finding.

The documented agent invocation is disabled; ai_chat performs no analysis and returns no result.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The agent invocation is commented out, and accessing stderr on the replacement dictionary raises an exception that is swallowed, causing ai_chat to return None. If used for sports-safety monitoring, this silently unavailable analysis could suppress warnings; the supplied source does not establish whether production analysis actually uses this method.

Content

No source excerpt is available for this finding.

FileUtil.open silently truncates existing files without disclosing its destructive behavior.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

Opening a path with mode 'w' immediately erases any existing contents, even before the caller writes anything. This generically named helper provides no docstring, explanatory comment, confirmation, or action log disclosing that behavior; exception tracing does not warn about successful truncation.

Content

No source excerpt is available for this finding.

Analysis requests can silently register an external user account, an undeclared side effect beyond sports-safety analysis.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

Ordinary HTTP requests can trigger a separate phoneLogin request with silent and register enabled, transmitting the current identifier and potentially creating a remote account. This side effect is not disclosed in the supplied sports-analysis description and creates privacy and account-lifecycle risks beyond merely performing an analysis.

Content

No source excerpt is available for this finding.

The HTTP helper silently performs remote login or registration using the current user's identifier.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The HTTP helper implicitly initiates login or registration when cached tokens are missing, using the current identifier as both openId and mobile. This conceals an identity-bearing remote operation inside routine analysis traffic; it is the same underlying account-registration issue identified by SDI-1, not evidence of a separate exploit.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This POST transmits an identity-bearing payload to the configured health-service endpoint during implicit authentication or registration. The caller prioritizes API_SECRET_KEY when selecting the identifier, so a configured secret can also be copied into the mobile and openId body fields; the endpoint's ownership and handling guarantees are not provided.

Content

Scanner excerpt · skills/smyx_common/scripts/util.py (reported line 561)May include surrounding context.

python
"source": ConstantEnum.DEFAULT__SKILL_HUB_NAME
            }
            try:
                _response = requests.post(_url, json=_data)
                if _response.status_code == 200:
                    _response_json = _response.json()
                    if _response_json and _response_json.get("success"):

Configuration loading silently creates directories and writes missing configuration files.

Low
Category
Output Handling
Confidence
96% confidence
Finding

At L017–L020, YamlUtil.load creates parent directories and writes a YAML file when the requested path is missing, without a comment, docstring, prompt, or log disclosing this side effect. BaseEnum.init_subclass calls this loader at L053 and L058, so merely importing the module can modify the filesystem rather than only read configuration.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 243)May include surrounding context.

python
username = getattr(model, "username", None)
            if username:
                column_names = self.__model__.__table__.columns.keys()
                update_data = {key: getattr(model, key) for key in column_names if key != "username"}
                return self.update_by_username(username, **update_data)

            return None

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 353)May include surrounding context.

python
column_names = self.__model__.__table__.columns.keys()

            for key in column_names:
                value = getattr(model, key)
                setattr(instance, key, value)

            session.commit()

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 326)May include surrounding context.

python
if filters:
                for key, value in filters.items():
                    query = query.filter(getattr(self.__model__, key) == value)

            if offset:
                query = query.offset(offset)

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 441)May include surrounding context.

python
if filters:
                for key, value in filters.items():
                    query = query.filter(getattr(self.__model__, key) == value)

            return query.scalar()
        finally:

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

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

python
elif isinstance(cur, dict):
                        cur = cur.get(part, default)
                    else:
                        cur = getattr(cur, part)
                return cur
            except Exception:
                return default