Trust Assessment
chromadb-memory received a trust score of 13/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 2 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, User query data exfiltration via configurable Ollama URL.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/msensintaffar/chromadb-memory/SKILL.md:35 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/msensintaffar/chromadb-memory/SKILL.md:35 | |
| HIGH | User query data exfiltration via configurable Ollama URL The skill sends user query text to a configurable Ollama API endpoint (`ollamaUrl`) for embedding generation. If a malicious actor convinces the user to configure `ollamaUrl` to an attacker-controlled server, user queries could be exfiltrated. The skill's description emphasizes 'No cloud APIs required — fully self-hosted,' but the implementation allows arbitrary URLs. Implement strict validation for `ollamaUrl` to ensure it points to a local or trusted private network address (e.g., `localhost`, `127.0.0.1`, private IP ranges). Alternatively, add a prominent warning in the documentation about the security implications of configuring `ollamaUrl` to an untrusted external endpoint. | LLM | scripts/index.ts:30 | |
| HIGH | User query embedding data exfiltration via configurable ChromaDB URL The skill sends user query embeddings (derived from user input) to a configurable ChromaDB API endpoint (`chromaUrl`) for semantic search. If a malicious actor convinces the user to configure `chromaUrl` to an attacker-controlled server, user query embeddings and the `collectionId` could be exfiltrated. The skill's description emphasizes 'No cloud APIs required — fully self-hosted,' but the implementation allows arbitrary URLs. Implement strict validation for `chromaUrl` to ensure it points to a local or trusted private network address (e.g., `localhost`, `127.0.0.1`, private IP ranges). Alternatively, add a prominent warning in the documentation about the security implications of configuring `chromaUrl` to an untrusted external endpoint. | LLM | scripts/index.ts:60 |
Scan History
Embed Code
[](https://skillshield.io/report/32c46fd70846334a)
Powered by SkillShield