Back to skill

Security audit

TransWeb 应用助手

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because scanners report that project configuration could send an environment-supplied API key to an untrusted endpoint, and its reference describes making generated results anonymously accessible.

The verdict is suspicious, so consider the reported API key exposure and anonymous sharing risks before installing. The script analysis is partial, which leaves some evidence incomplete; the verdict does not establish malicious intent.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/transweb_ai.py
Finding

Automatically discovered project configuration can redirect an environment-supplied API key

Content
View full analysis

Impact

The attacker-controlled endpoint receives the full TransWeb API key. It can subsequently exercise the victim's account permissions within the key's scopes; generation commands can also disclose submitted task content.

Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (42)

Tainted flow: 'payload' from sys.stdin.read (line 411, user input) → subprocess.run (code execution)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

External input (network, user) flows to a code execution sink. This enables remote code execution or command injection.

Content

Scanner excerpt · scripts/transweb_ai.py (reported line 420)May include surrounding context.

python
]
    cmd.append(url)
    try:
        proc = subprocess.run(
            cmd,
            input=payload,
            stdout=subprocess.PIPE,

Tainted flow: 'url' from os.environ.get (line 2155, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/transweb_ai.py (reported line 1400)May include surrounding context.

python
)
        return (proc.stdout or b"").decode("utf-8", errors="replace")
    try:
        with urllib.request.urlopen(url, timeout=timeout) as response:
            return response.read().decode("utf-8", errors="replace")
    except Exception as exc:  # noqa: BLE001
        raise SkillError(

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
python3 scripts/transweb_ai.py demo --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
python3 scripts/transweb_ai.py demo list --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
python3 scripts/transweb_ai.py demo run --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
python3 scripts/transweb_ai.py demo ppt --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
python3 scripts/transweb_ai.py ppt --input "做一份季度汇报 PPT" --dry-run --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
python3 scripts/transweb_ai.py run --ids 11111111111111111111111111111111 --input "先写大纲" --dry-run --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

md
python3 scripts/transweb_ai.py list --dry-run --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

md
python3 scripts/transweb_ai.py selftest --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md
python3 scripts/transweb_ai.py config show

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.

md
python3 scripts/transweb_ai.py configure --verify

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

md
python3 scripts/transweb_ai.py configure --api-key ak_live_NEW --verify

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 149)May include surrounding context.

md
python3 scripts/transweb_ai.py configure --profile work --api-key ak_live_WORK --verify

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 152)May include surrounding context.

md
python3 scripts/transweb_ai.py config list

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
python3 scripts/transweb_ai.py config use work

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
python3 scripts/transweb_ai.py config use default

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
python3 scripts/transweb_ai.py config remove work

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 162)May include surrounding context.

md
python3 scripts/transweb_ai.py ppt --profile work --input "..."

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 163)May include surrounding context.

md
python3 scripts/transweb_ai.py list --profile work --query "PPT"

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.

md
python3 scripts/transweb_ai.py selftest --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 178)May include surrounding context.

md
python3 scripts/transweb_ai.py --version

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 188)May include surrounding context.

md
python3 scripts/transweb_ai.py ppt --input "主题、章节、每页要点或完整需求描述" --json

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 218)May include surrounding context.

md
python3 scripts/transweb_ai.py list --json --limit 50

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 267)May include surrounding context.

md
python3 scripts/transweb_ai.py list --query "商业方案" --limit 10