← back to mcp-builder

SkillSpector · mcp-builder

independent scanner by NVIDIA · skill by seaworld008 · how it works ↗

FAILmax severity: CRITICALrisk score: 86

Without declared permissions the skill's intent is opaque and cannot be validated.; npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.; Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; +5 more

scanned 2026-08-23

Findings (14)

MEDIUMMCP Least Privilegeconfidence: 0.7

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMData Exfiltrationconfidence: 0.5

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

reference/node_mcp_server.md

MEDIUMData Exfiltrationconfidence: 0.5

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

reference/python_mcp_server.md

LOWExcessive Agencyconfidence: 0.7

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

LICENSE.txt

LOWExcessive Agencyconfidence: 0.7

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

LICENSE.txt

MEDIUMExcessive Agencyconfidence: 0.85

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

SKILL.md

MEDIUMExcessive Agencyconfidence: 0.85

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

SKILL.md

HIGHPrivilege Escalationconfidence: 0.7

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

reference/mcp_best_practices.md

HIGHPrivilege Escalationconfidence: 0.6

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

scripts/connections.py

HIGHPrivilege Escalationconfidence: 0.6

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

scripts/evaluation.py

LOWSupply Chainconfidence: 0.5

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

scripts/requirements.txt

LOWSupply Chainconfidence: 0.5

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

scripts/requirements.txt

HIGHSupply Chainconfidence: 0.8

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

scripts/requirements.txt

What the verdicts mean

SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.

PASS

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete