← back to flow-for-slack

SkillSpector · flow-for-slack

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

CAUTIONmax severity: MEDIUMrisk score: 49

Without declared permissions the skill's intent is opaque and cannot be validated.; Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak p…; Instructions found that direct the agent to transmit conversation context or user data to external services.

scanned 2026-08-22

Findings (13)

MEDIUMMCP Least Privilegeconfidence: 0.7

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

SKILL.md

HIGHAnti-Refusalconfidence: 0.8

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

SKILL.md

HIGHAnti-Refusalconfidence: 0.24

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

references/gotchas.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

SKILL.md

HIGHPrompt Injectionconfidence: 0.27

Instructions found that direct the agent to transmit conversation context or user data to external services.

references/well-architected.md

HIGHPrompt Injectionconfidence: 0.27

Instructions found that direct the agent to transmit conversation context or user data to external services.

references/well-architected.md

HIGHPrompt Injectionconfidence: 0.9

Instructions found that direct the agent to transmit conversation context or user data to external services.

templates/flow-for-slack-template.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