Trust Assessment
serper-search received a trust score of 78/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 4 findings: 0 critical, 0 high, 3 medium, and 1 low severity. Key findings include Missing required field: name, Unpinned npm dependency version, Node lockfile missing.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/samoppakiks/serper-search/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency '@sinclair/typebox' is not pinned to an exact version ('^0.32.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/samoppakiks/serper-search/package.json | |
| MEDIUM | Potential Prompt Injection via Search Results The `serper_search` tool takes a user-controlled `query` and sends it to an external search API (Serper.dev). The raw search results, including titles and snippets from external websites, are then returned directly to the host LLM. If these search results contain malicious instructions (e.g., 'ignore previous instructions' or data exfiltration attempts), the LLM could be manipulated to follow them. The skill itself does not sanitize or filter the content of the search results before returning them. Implement robust output sanitization or filtering of search results before returning them to the LLM, specifically looking for patterns indicative of prompt injection. Alternatively, ensure the host LLM's architecture is resilient to interpreting tool outputs as new instructions, or consider summarizing results instead of returning raw snippets. | LLM | index.ts:90 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/samoppakiks/serper-search/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/eda0514c5a18a164)
Powered by SkillShield