← back to paw-cra-agent-creative-director
SkillSpector · paw-cra-agent-creative-director
independent scanner by NVIDIA · skill by pawbytes · how it works ↗
subprocess module calls execute external commands. Without careful input validation, this enables command injection.; Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.; Without declared permissions the skill's intent is opaque and cannot be validated.; +1 more
scanned 2026-08-23
Findings (14)
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tests/test-init-memory.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tests/test-init-memory.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tests/test-tool-discovery.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tests/test-tool-discovery.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tests/test-tool-discovery.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tool-discovery.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tool-discovery.py
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/tool-discovery.py
Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.
scripts/render-template.py
Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.
scripts/render-template.py
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md
Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
scripts/tool-discovery.py
Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
scripts/tool-discovery.py
Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
scripts/tool-discovery.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