Trust Assessment
search-memory received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via User Query.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via User Query The skill's `Quick Start` section demonstrates a command `scripts/search-memory.py "your query" --top 5` where "your query" is intended to be user-provided input. If the AI agent directly interpolates untrusted user input into this shell command without proper sanitization or escaping, it could lead to arbitrary command execution. An attacker could craft a malicious query (e.g., `"; rm -rf /"`) to execute arbitrary commands on the host system. The AI agent executing this command must ensure that any user-provided input for "your query" is properly sanitized and shell-escaped before being passed to the `scripts/search-memory.py` command. For example, using `shlex.quote()` in Python or equivalent functions in other languages. The `search-memory.py` script itself should also validate and sanitize its arguments to prevent injection if the shell escaping fails or is bypassed. | LLM | SKILL.md:16 |
Scan History
Embed Code
[](https://skillshield.io/report/30834aaef3cbbbcd)
Powered by SkillShield