Trust Assessment
scripture-curated received a trust score of 81/100, 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, 0 high, 3 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, Missing required field: name, Potential Prompt Injection via Web Search Tool.
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 | |
|---|---|---|---|---|
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/snail3d/clawd/skills/scripture-curated/scripts/scripture-curated.js:494 | |
| 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/snail3d/clawd/skills/scripture-curated/SKILL.md:1 | |
| MEDIUM | Potential Prompt Injection via Web Search Tool The `NewsSearch` class in `scripts/news-search.js` is designed to construct search queries from input parameters (`query` or `topic`) and pass them to an external `web_search` tool, as indicated by the comment `// In actual implementation, this would call web_search tool`. If this `web_search` tool is an LLM-based agent, and user-controlled input is passed to `NewsSearch.search()` or `NewsSearch.searchTopic()` without proper sanitization, it could lead to prompt injection. An attacker could craft input to manipulate the behavior of the underlying LLM-based search tool. Ensure all user-controlled input passed to `NewsSearch.search()` or `NewsSearch.searchTopic()` is thoroughly sanitized before being used to construct queries for an LLM-based `web_search` tool. Implement strict input validation and consider using a dedicated prompt templating or sanitization library to prevent malicious instructions from reaching the LLM. | LLM | scripts/news-search.js:25 |
Scan History
Embed Code
[](https://skillshield.io/report/2d63e63b744173be)
Powered by SkillShield