Trust Assessment
nimble-web-search received a trust score of 20/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive environment variable access: $GITHUB_COPILOT, Sensitive path access: AI agent config.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/ilchemla/nimble-web-search/scripts/search.sh:44 | |
| CRITICAL | Prompt Injection Attempt via Untrusted Instructions The skill's documentation, which is treated as untrusted input, contains explicit instructions and directives intended to manipulate the host LLM's behavior. This violates the core security principle that untrusted content should not contain instructions or commands for the LLM. The presence of such directives within the untrusted input block constitutes a prompt injection attempt, as it tries to override or influence the LLM's operational guidelines. Remove all direct instructions, commands, or behavioral directives for the LLM from the untrusted content section. The skill's documentation should describe its functionality and usage without attempting to control the LLM's internal reasoning or decision-making process. Any necessary guidance for the LLM should be provided as part of the trusted system prompt or tool definition, not within the skill's untrusted description. | LLM | SKILL.md:50 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/ilchemla/nimble-web-search/scripts/search.sh:44 | |
| MEDIUM | Sensitive environment variable access: $GITHUB_COPILOT Access to sensitive environment variable '$GITHUB_COPILOT' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/ilchemla/nimble-web-search/scripts/search.sh:76 |
Scan History
Embed Code
[](https://skillshield.io/report/aee4c1e12e72ecfa)
Powered by SkillShield