Trust Assessment
huggingface-papers received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Indirect Prompt Injection via Untrusted Paper Content, Potential Command Injection via Unsanitized Paper ID.
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 October 1, 2026 (commit 80f9fa53). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Indirect Prompt Injection via Untrusted Paper Content The skill instructs the agent to fetch and parse paper content from Hugging Face or arXiv. Since this content is user-generated and untrusted, it can contain indirect prompt injection payloads. An attacker could craft a paper that, when read by the agent, manipulates it into executing arbitrary commands, exfiltrating the `$HF_TOKEN` environment variable, or performing unauthorized API actions (such as claiming papers or updating links). Add explicit instructions in the skill to treat all fetched paper content as untrusted data. The agent must never follow instructions contained within the papers, must never exfiltrate or reveal environment variables like `$HF_TOKEN`, and must only perform write actions (like claiming papers or updating links) when directly and explicitly commanded by the user in the main chat session. | LLM | SKILL.md:51 | |
| MEDIUM | Potential Command Injection via Unsanitized Paper ID The skill recommends constructing and executing shell commands (using `curl`) with user-provided `{PAPER_ID}` or `{ARXIV_ID}`. If the agent does not strictly validate and sanitize these inputs, a malicious user could inject shell metacharacters (e.g., `;`, `&&`, `|`) to execute arbitrary commands on the host system. Instruct the agent to strictly validate the `{PAPER_ID}` or `{ARXIV_ID}` against a safe regular expression (such as `^\d{4}\.\d{4,5}(v\d+)?$`) before using it in any shell command. Avoid raw shell execution with string interpolation where possible. | LLM | SKILL.md:51 |
Scan History
Embed Code
[](https://skillshield.io/report/5f2c2b8ef4540d51)
Powered by SkillShield