SkillSpector · baidu-drive

independent scanner by NVIDIA · skill by infometa · how it works ↗

WARNINGmax severity: HIGHrisk score: 66

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.; Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks an…; Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous …

scanned 2026-08-23

Findings (4)

HIGHData Exfiltrationconfidence: 0.6

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

reference/bdpan-commands.md

HIGHOutput Handlingconfidence: 0.85

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

reference/bdpan-commands.md

HIGHTool Misuseconfidence: 0.85

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

SKILL.md

HIGHTool Misuseconfidence: 0.75

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

reference/bdpan-commands.md

What the verdicts mean

SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.

PASS

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNINGthis skill

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete