Trust Assessment
paper-fetcher received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 6 findings: 2 critical, 2 high, 1 medium, and 1 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Path Traversal via output_dir parameter.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings6
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/biohackerrrrrr/paper-fetcher/scripts/fetch_paper.py:56 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/biohackerrrrrr/paper-fetcher/scripts/fetch_paper.py:95 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'fetch_paper'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/biohackerrrrrr/paper-fetcher/scripts/fetch_paper.py:56 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'fetch_paper'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/biohackerrrrrr/paper-fetcher/scripts/fetch_paper.py:95 | |
| MEDIUM | Path Traversal via output_dir parameter The `fetch_paper` function accepts an `output_dir` parameter which is directly used to construct the path for saving downloaded PDFs. While the `SKILL.md` documentation specifies `research/papers/` as the intended save location, the script's implementation allows arbitrary paths, including those containing `../` sequences. If the host LLM is prompted to provide a malicious `output_dir` (e.g., `../../../../etc`), the skill would attempt to write files to unintended locations outside the designated workspace. This could lead to data corruption, denial of service by overwriting critical system files, or potentially arbitrary code execution if a malicious file is placed in an executable path. Implement strict validation for the `output_dir` parameter to ensure it is a subdirectory of the intended workspace or a temporary directory. For example, resolve the path and verify it starts with a known, safe base directory. Additionally, reinforce LLM instructions to always use a secure, predefined path for `output_dir` and never to use user-provided paths. | LLM | scripts/fetch_paper.py:29 | |
| LOW | Unencoded DOI in curl URL construction The `doi` parameter, which is user-controlled, is directly appended to the `sci_hub_domain` to form the `sci_hub_url` without proper URL encoding using `urllib.parse.quote`. While `clean_doi` performs some sanitization (removing prefixes and replacing slashes), it does not encode all special URL characters (e.g., `(`, `)`, `[`, `]`, `;`, etc.) that can appear in valid DOIs. Although `curl` is generally robust when arguments are passed as a list, passing unencoded user input as part of a URL path segment is a security best practice violation and could, in rare edge cases or with specific `curl` versions/configurations, lead to misinterpretation of the URL or unexpected behavior. It is more likely to cause functional errors than command injection, but the potential risk exists. Use `urllib.parse.quote` to URL-encode the DOI before appending it to the `sci_hub_domain`. For example, `sci_hub_url = f"{sci_hub_domain}/{quote(doi, safe='')}"` to ensure all special characters are properly handled. | LLM | scripts/fetch_paper.py:37 |
Scan History
Embed Code
[](https://skillshield.io/report/b27692254a363005)
Powered by SkillShield