← back to walkthrough-gif

SkillSpector · walkthrough-gif

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

WARNINGmax severity: HIGHrisk score: 62

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.; Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.; Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.; +2 more

scanned 2026-08-23

Findings (11)

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

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

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

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.

references/output-pipeline.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.

references/stagehand-patterns.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.

references/stagehand-patterns.md

HIGHData Exfiltrationconfidence: 0.85

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

SKILL.md

HIGHPrivilege Escalationconfidence: 0.6

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

SKILL.md

HIGHPrivilege Escalationconfidence: 0.18

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

references/stagehand-patterns.md

HIGHTool Misuseconfidence: 0.255

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

references/output-pipeline.md

HIGHYARA Matchconfidence: 0.375

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

references/stagehand-patterns.md

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

WARNINGthis skill

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete