← back to cue-your-ai-research-assistant

SkillSpector · cue-your-ai-research-assistant

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

FAILmax severity: CRITICALrisk score: 100

Without declared permissions the skill's intent is opaque and cannot be validated.; Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.; Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; +6 more

scanned 2026-08-23

Findings (20)

MEDIUMMCP Least Privilegeconfidence: 0.7

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

SKILL.md

HIGHMCP Tool Poisoningconfidence: 0.85

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

SKILL.md

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/integrated-search.sh

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/integrated-search.sh

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/integrated-search.sh

MEDIUMData Exfiltrationconfidence: 0.6

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/integrated-search.sh

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/search-executor.sh

MEDIUMData Exfiltrationconfidence: 0.6

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

backups/scripts-v1.0.3-20260226-015020/executor/search-executor.sh

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

src/cron/monitor-daemon.js

MEDIUMData Exfiltrationconfidence: 0.7

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

src/cron/monitor-daemon.js

MEDIUMData Exfiltrationconfidence: 0.6

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

src/cron/monitor-daemon.js

MEDIUMData Exfiltrationconfidence: 0.6

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

src/cron/monitor-daemon.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/cli.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/index.js

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

src/index.js

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

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete