← back to epub

SkillSpector · epub

independent scanner by NVIDIA · skill by theheavenlyd3mon · how it works ↗

WARNINGmax severity: HIGHrisk score: 76

Without declared permissions the skill's intent is opaque and cannot be validated.; Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.; +2 more

scanned 2026-08-23

Findings (17)

MEDIUMMCP Least Privilegeconfidence: 0.7

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

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.

scripts/epub-extract-knowledge

HIGHData Exfiltrationconfidence: 0.7

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/epub-extract-knowledge

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

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.

scripts/epub-validate

HIGHOutput Handlingconfidence: 0.85

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/epub-batch

HIGHOutput Handlingconfidence: 0.85

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/epub-convert

HIGHOutput Handlingconfidence: 0.85

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/epub-validate

HIGHOutput Handlingconfidence: 0.95

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/test_epub_skill.sh

HIGHOutput Handlingconfidence: 0.95

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

scripts/test_epub_skill.sh

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