Trust Assessment
conversation-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 5 findings: 0 critical, 1 high, 3 medium, and 1 low severity. Key findings include Suspicious import: requests, Unpinned npm dependency version, Node lockfile missing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Conversation Data Exfiltration to Third-Party API The skill sends the user's full conversation history (`chat_list`) and any provided `history_summary` to an external, hardcoded third-party API endpoint (`https://iautomark.sdm.qq.com/assistant-analyse/v1/assistant/poc/summary/trigger`). This constitutes data exfiltration, as potentially sensitive user conversation data is transmitted outside the user's local environment to a service not directly controlled by the user or the agent's platform. Inform users explicitly about the data transfer to a third-party service. Provide options for users to consent to this data sharing, configure an alternative API endpoint, or disable the skill if data privacy is a concern. Consider implementing local processing if feasible to avoid external data transfer. | LLM | scripts/conversation_summary.py:34 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lyue82665-droid/conversation-summary/scripts/conversation_summary.py:8 | |
| MEDIUM | Unpinned npm dependency version Dependency 'requests' is not pinned to an exact version ('^2.31.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/lyue82665-droid/conversation-summary/package.json | |
| MEDIUM | Hardcoded External API Dependency (Supply Chain Risk) The skill relies on a hardcoded external API endpoint (`https://iautomark.sdm.qq.com/assistant-analyse/v1/assistant/poc/summary/trigger`) for its core functionality. This introduces a supply chain risk: if the external API becomes unavailable, malicious, or changes its terms of service, the skill's functionality, security, and privacy guarantees could be compromised without user intervention or awareness. The skill's operation is entirely dependent on the continued integrity and availability of this third-party service. Allow the API endpoint to be configurable by the user or administrator, rather than hardcoded. Document the dependency on this third-party service clearly. Consider providing an alternative local processing option or a fallback mechanism if the external API is critical. | LLM | scripts/conversation_summary.py:19 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/lyue82665-droid/conversation-summary/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/fbf3b0326807967a)
Powered by SkillShield