SkillSpector · claw-orchestrator
independent scanner by NVIDIA · skill by gabrielmoreira · how it works ↗
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.; Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.; Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credenti…; +5 more
scanned 2026-08-22
Findings (12)
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/acp.md
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/autoloop.md
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
references/ultraapp.md
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
references/autoloop.md
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
references/multi-engine.md
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
references/multi-engine.md
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
references/tools.md
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
references/claude-cli-tracking.md
Instructions found that direct the agent to transmit conversation context or user data to external services.
references/tools.md
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
references/getting-started.md
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
references/multi-engine.md
Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
references/multi-engine.md
What the verdicts mean
SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.
Overall severity LOW (risk score in the safe range)
Overall severity MEDIUM
Overall severity HIGH
Overall severity CRITICAL
Scan could not complete