Trust Assessment
meeting-minutes-generator received a trust score of 75/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Missing required field: name, Potential Prompt Injection via Markdown Generation, Arbitrary File Write via `export_all_actions`.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Write via `export_all_actions` The `export_all_actions` method allows writing an Excel file to an arbitrary `output_path` provided by the user. This poses a significant security risk, as a malicious actor could specify paths to sensitive system locations (e.g., `/etc/passwd`, `/root/.ssh/authorized_keys`), overwrite critical files, or write to network shares for data exfiltration. This constitutes both an excessive permission and a data exfiltration risk. Restrict the `output_path` to a predefined, sandboxed directory that is inaccessible to other parts of the system. Implement strict path validation to prevent directory traversal attacks (e.g., `../`, absolute paths outside the sandbox). Consider using a temporary file system or a dedicated output directory for all generated files. | LLM | SKILL.md:238 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/datadrivenconstruction/meeting-minutes-generator/SKILL.md:1 | |
| MEDIUM | Potential Prompt Injection via Markdown Generation The `generate_minutes_document` method constructs a markdown string by directly embedding various user-provided data fields (e.g., `title`, `discussion`, `description`, `name`, `company`, `role`, `presenter`, `assigned_to`). If this generated markdown is subsequently fed into an LLM without proper sanitization or instruction framing, a malicious user could inject new instructions or manipulate the LLM's behavior by crafting specific inputs for these fields. Implement robust input sanitization for all user-controlled text fields before they are incorporated into the generated markdown. Alternatively, ensure that any downstream LLM calls that consume this markdown explicitly treat it as data/content rather than instructions, for example, by wrapping it in specific data tags or using a dedicated content-only input parameter. | LLM | SKILL.md:190 |
Scan History
Embed Code
[](https://skillshield.io/report/5d0b88e2b7da7aa8)
Powered by SkillShield