Trust Assessment
faiss received a trust score of 84/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Insecure Deserialization Example.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Insecure Deserialization Example The skill documentation provides a code example for loading a FAISS vector store using LangChain with `allow_dangerous_deserialization=True`. This flag explicitly enables potentially unsafe deserialization of Python objects from the loaded index. If a user loads an index from an untrusted source using this example, it could lead to arbitrary code execution (RCE) due to pickle deserialization vulnerabilities. Advise users against setting `allow_dangerous_deserialization=True` when loading vector stores from untrusted or unverified sources. If this functionality is strictly necessary, add a prominent warning in the documentation about the associated security risks and recommend strict source verification. Alternatively, explore safer serialization formats or methods if available for the specific use case. | LLM | SKILL.md:167 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/62d9919a51c4c2d1)
Powered by SkillShield