Trust Assessment
pymupdf-pdf received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unrestricted output directory allows writing to arbitrary filesystem locations.
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 | |
|---|---|---|---|---|
| MEDIUM | Unrestricted output directory allows writing to arbitrary filesystem locations The `pymupdf_parse.py` script allows the user to specify an arbitrary output root directory via the `--outroot` argument. While the `pdf_path.stem` component is safely derived, the `args.outroot` value is used directly to construct the output path without sanitization or restriction. An attacker could craft a prompt to an AI agent to invoke this skill with a sensitive `--outroot` path (e.g., `/etc`, `/usr/local/bin`, or a path traversal like `../../../../tmp`) to write the parsed PDF content to unintended or sensitive system locations. This could lead to system disruption, overwriting critical files, or potentially privilege escalation if combined with other vulnerabilities and sufficient write permissions in the execution environment. Implement validation for the `--outroot` argument to restrict it to a safe, designated output directory (e.g., within the skill's sandbox, a temporary directory, or a user-specific data directory). Alternatively, ensure the execution environment for the skill has strict filesystem write restrictions to prevent writing to sensitive system paths. | LLM | scripts/pymupdf_parse.py:70 |
Scan History
Embed Code
[](https://skillshield.io/report/2f56863284e8aaf4)
Powered by SkillShield