← back to llm-council

SkillSpector · llm-council

independent scanner by NVIDIA · skill by 0xharryriddle · how it works ↗

WARNINGmax severity: HIGHrisk score: 58

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.; Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial…; +1 more

scanned 2026-08-23

Findings (6)

MEDIUMDangerous Code Executionconfidence: 0.7

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

scripts/llm_council.py

MEDIUMDangerous Code Executionconfidence: 0.7

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

scripts/llm_council.py

MEDIUMMCP Least Privilegeconfidence: 0.7

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

SKILL.md

MEDIUMExcessive Agencyconfidence: 0.75

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

scripts/llm_council.py

HIGHSystem Prompt Leakageconfidence: 0.85

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

scripts/llm_council.py

HIGHSystem Prompt Leakageconfidence: 0.85

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

scripts/llm_council.py

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