SkillSpector · 007
independent scanner by NVIDIA · skill by FrancoStino · how it works ↗
Without declared permissions the skill's intent is opaque and cannot be validated.; Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a di…; Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modi…; +8 more
scanned 2026-08-23
Findings (20)
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
references/ai-agent-security.md
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
references/ai-agent-security.md
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
references/ai-agent-security.md
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.
scripts/scanners/dependency_scanner.py
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.
scripts/scanners/dependency_scanner.py
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
references/ai-agent-security.md
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
references/ai-agent-security.md
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
references/stride-pasta-guide.md
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/config.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/config.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/config.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/config.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/full_audit.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/full_audit.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/scanners/dependency_scanner.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/scanners/dependency_scanner.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/scanners/secrets_scanner.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/scanners/secrets_scanner.py
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
scripts/scanners/secrets_scanner.py
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