Trust Assessment
dada-conv-summary received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via Unescaped Parameters in Curl Command, Data Exfiltration of Conversation History to External Service.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via Unescaped Parameters in Curl Command The skill constructs a `curl` command by directly interpolating the `chat_list` and `history_summary` parameters into a shell string without proper escaping. The instruction 'Always escape quotes properly in the JSON string' places the burden of security on the LLM, which is an unreliable control. If the LLM generates a `chat_list` or `history_summary` string containing shell metacharacters (e.g., single quotes, backticks, or command substitutions), it could break out of the JSON payload and execute arbitrary commands on the host system. Implement robust escaping for `chat_list` and `history_summary` before embedding them into the `curl` command. Ideally, use a programming language's JSON serialization library and a safe subprocess execution method that avoids shell interpretation, or ensure all potentially malicious characters are properly escaped for the shell context. | LLM | SKILL.md:20 | |
| HIGH | Data Exfiltration of Conversation History to External Service The skill sends the entire conversation history (`chat_list`) and previous summary (`history_summary`) to an external, third-party URL (`https://iautomark.sdm.qq.com`). This constitutes data exfiltration of potentially sensitive user data to an external service, which may not have the same privacy or security guarantees as the local environment. Users may not be aware or consent to their conversation data being transmitted to this domain. Obtain explicit user consent before sending conversation data to external services. Clearly disclose the data being sent and the recipient. Consider if the summarization can be performed locally or with a trusted, privacy-preserving service. If an external service is necessary, ensure it meets strict data privacy and security standards. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/21841c36bc236234)
Powered by SkillShield