Trust Assessment
memory-lite 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 Shell Command Injection via grep 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 12, 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 | Shell Command Injection via grep query The `scripts/memory_grep.sh` script directly interpolates the user-provided query `$q` into a `grep` command. Although `grep` options are protected by `--`, shell metacharacters within `$q` (e.g., `$(command)`, backticks) will be expanded and executed by the shell before `grep` is invoked. This allows an attacker to execute arbitrary commands on the host system. To prevent shell expansion of the query, pipe the query string to `grep` using `-f /dev/stdin`. This ensures the shell treats the query as a literal string for `grep`'s pattern matching, rather than attempting to execute it. Replace the vulnerable line with: `printf '%s\n' "$q" | grep -RInI --exclude-dir=.git --exclude-dir=node_modules --exclude-dir=dist -f /dev/stdin "./MEMORY.md" "./memory" 2>/dev/null || true` | LLM | scripts/memory_grep.sh:14 |
Scan History
Embed Code
[](https://skillshield.io/report/0a0ab7a0394369c2)
Powered by SkillShield