SkillSpector · markitdown
independent scanner by NVIDIA · skill by JoshuaShepherd · 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 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.; Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.; +1 more
scanned 2026-08-22
Findings (4)
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
scripts/convert_with_ai.py
The skill uses 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
scripts/batch_convert.py
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
SKILL.md
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.
scripts/convert_with_ai.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