Security Audit
developer-growth-analysis
github.com/skillcreatorai/Ai-Agent-SkillsTrust Assessment
developer-growth-analysis 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 Sensitive Local Chat History Exfiltrated to External Service.
The analysis covered 4 layers: dependency_graph, static_code_analysis, manifest_analysis, llm_behavioral_safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 6195a031). 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 | Sensitive Local Chat History Exfiltrated to External Service The skill explicitly instructs the LLM to read the user's local Claude chat history from `~/.claude/history.jsonl`. This file can contain highly sensitive information, including user messages, project details, and `pastedContents` (which may include code, API keys, or other confidential data). The skill then analyzes this data and sends a 'complete report' derived from it to the user's Slack DMs using `Rube MCP`. While intended for the user's own DMs, this constitutes an external transfer of potentially sensitive local data, posing a risk if the Slack integration or the `Rube MCP` tool is compromised, or if the user's Slack account is not adequately secured. This is a direct instruction for data exfiltration. 1. **Data Minimization**: Strictly filter the data read from `history.jsonl` to only include necessary fields, excluding highly sensitive `pastedContents` unless explicitly required and consented to. 2. **Redaction/Anonymization**: Implement robust redaction or anonymization techniques for any sensitive data before it is included in the report or sent externally. 3. **Explicit User Consent**: Clearly inform the user about the specific types of data being accessed and the external services (Slack) to which derived information will be sent, requiring explicit consent. 4. **Secure Communication**: Ensure the `Rube MCP` tool uses secure, encrypted channels for all external communications and that Slack integration follows best practices for OAuth and token management. 5. **Local-Only Option**: Provide an option for users to generate and view the report locally without sending it to an external service. | Unknown | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/6983be5f6ea9b45a)
Powered by SkillShield