T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:77- Finding
Predictable Shared Temporary File Enables Symlink and Output-Substitution Attacks
- Content
View full analysis
- Remediation
View remediation
Security audit
TTS文字转语音
Security checks for vulnerabilities and agentic risk
Overview
This skill does what it says: converts user text to speech through a disclosed remote TTS endpoint, but users should avoid sending sensitive text and should use safer temporary filenames.
Install only if you are comfortable sending the text you convert to tts.wangwangit.com. Do not use it for secrets, credentials, regulated data, or confidential documents unless you have approved that provider. Prefer a unique private temporary output file instead of the documented fixed /tmp path.
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 (2)
other
Warning
- Location
SKILL.md:15- Finding
User-Provided Text Is Disclosed to an External TTS Provider Without Privacy Safeguards
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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
Findings (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill sends user-provided text to an external third-party TTS service but does not clearly warn users that their content leaves the system and is processed by another provider. This can expose sensitive, personal, or confidential text if users assume local processing or first-party handling.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 98% confidence
- Finding
The curl example explicitly transmits text content to an external TTS service and writes the returned audio to a local file. Although this is expected for TTS, the lack of warning or safeguards makes accidental disclosure of confidential user content more likely.
- Content
单条生成：
bash curl -s -X POST 'https://tts.wangwangit.com/v1/audio/speech' \ -H 'content-type: application/json' \ -d '{"input":"你好","voice":"zh-CN-YunyangNeural","speed":0.9,"pitch":"0","style":"general"}' \ -o /tmp/tts_output.mp3
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 98% confidence
- Finding
The Python example performs a POST request to an external TTS endpoint with raw user text in the JSON body, creating an external data transmission path. In this skill's context, the transfer is the core feature, but it remains risky because users may submit sensitive text and the skill gives no consent, minimization, or provider trust guidance.
- Content
md "pitch": pitch, "style": style } res = requests.post(ttsurl, json=jd, timeout=300) res.raise_for_status() with open(output_file, "wb") as f: f.write(res.content)
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The natural-language instructions throughout the skill are Chinese-only, which effectively forces a specific language without any opt-in or documented regional justification. The stated policy requires language constraints to be optional or clearly justified.
- Content