← back to axolotl

SkillSpector · axolotl

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

PASSmax severity: LOWrisk score: 20

Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.; Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.; Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

scanned 2026-08-23

Findings (4)

MEDIUMMCP Rug Pullconfidence: 0.75

Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

references/other.md

HIGHMemory Poisoningconfidence: 0.255

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

references/other.md

HIGHMemory Poisoningconfidence: 0.255

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

references/other.md

HIGHSystem Prompt Leakageconfidence: 0.255

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

references/api.md

What the verdicts mean

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

PASSthis skill

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete