← back to bmad-teach-me-testing

SkillSpector · bmad-teach-me-testing

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

CAUTIONmax severity: MEDIUMrisk score: 34

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstrea…; Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modi…

scanned 2026-08-23

Findings (3)

HIGHAnti-Refusalconfidence: 0.7

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

steps-c/step-03-session-menu.md

MEDIUMExcessive Agencyconfidence: 0.8

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

steps-c/step-04-session-02.md

MEDIUMExcessive Agencyconfidence: 0.85

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

workflow-plan-teach-me-testing.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)

CAUTIONthis skill

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete