Trust Assessment
session-wrap-up 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 Automatic `git push` of potentially sensitive workspace data.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Automatic `git push` of potentially sensitive workspace data The skill is designed to write session summaries, discussed topics, decisions, and even 'Commands, configs, or code that worked' to local memory files (`memory/YYYY-MM-DD.md`, `MEMORY.md`, `notes/`). Crucially, it then executes `git add -A`, which stages *all* changes in the current Git repository, followed by an automatic `git push` to a remote repository without user confirmation. This means any sensitive information (e.g., API keys, internal system details, confidential discussions, code snippets with secrets) that the LLM includes in these memory files, or any other sensitive files present in the workspace that are not explicitly ignored by `.gitignore`, will be automatically committed and pushed to a remote Git repository. The skill explicitly states 'The wrap-up `git push` is **automatic** (no confirmation prompt).' This poses a significant data exfiltration risk. 1. **Require user confirmation for `git push`:** Implement a step where the user reviews the staged changes (`git status`) and explicitly confirms the `git commit` and `git push` operations. 2. **Limit `git add` scope:** Instead of `git add -A`, modify the skill to explicitly stage only the intended memory files and directories (e.g., `git add memory/ MEMORY.md notes/`). 3. **Strengthen `.gitignore`:** Ensure a robust `.gitignore` file is in place in the workspace to prevent sensitive files (e.g., `.env`, credentials, private keys, temporary files) from being accidentally staged and committed. 4. **Sanitize sensitive data:** Instruct the LLM to redact or generalize any highly sensitive information when writing to memory files. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/ebbcaea64a7fd141)
Powered by SkillShield