SkillSpector · generate-visuals
independent scanner by NVIDIA · skill by lionelndong · how it works ↗
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.; The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.; Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, a…; +2 more
scanned 2026-08-23
Findings (9)
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
scripts/capture_screenshot.py
The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
scripts/capture_screenshot.py
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
scripts/capture_screenshot.py
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.
scripts/capture_screenshot.py
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.
scripts/generate_image.py
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.
scripts/generate_image.py
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.
scripts/run_action_shot.py
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
scripts/generate_image.py
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
scripts/generate_image.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