SkillSpector · xlsx

independent scanner by NVIDIA · skill by ahang1598 · how it works ↗

FAILmax severity: CRITICALrisk score: 100

subprocess module calls execute external commands. Without careful input validation, this enables command injection.; Without declared permissions the skill's intent is opaque and cannot be validated.; Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.; +4 more

scanned 2026-08-22

Findings (20)

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/ecmadoc/auditors/revision_auditor.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/ecmadoc/auditors/revision_auditor.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/ecmadoc/lo_runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/ecmadoc/lo_runner.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/formula_refresh.py

MEDIUMDangerous Code Executionconfidence: 0.7

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

scripts/formula_refresh.py

MEDIUMMCP Least Privilegeconfidence: 0.7

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

HIGHData Exfiltrationconfidence: 0.6

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

scripts/ecmadoc/lo_runner.py

HIGHOutput Handlingconfidence: 0.95

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/formula_refresh.py

HIGHOutput Handlingconfidence: 0.95

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/formula_refresh.py

HIGHPrompt Injectionconfidence: 0.6

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

scripts/ecmadoc/schemas/ecma/fouth-edition/opc-contentTypes.xsd

HIGHPrompt Injectionconfidence: 0.6

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

scripts/ecmadoc/schemas/ecma/fouth-edition/opc-coreProperties.xsd

HIGHPrompt Injectionconfidence: 0.6

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

scripts/ecmadoc/schemas/ecma/fouth-edition/opc-relationships.xsd

MEDIUMRogue Agentconfidence: 0.75