Shadow admin skill: permissive schema grants elevation under prompt injection
Summary
Skill advertised as user management or team onboarding exposes a tools schema with wildcarded permission scopes (admin, all, write-all). Under prompt-injection or hallucination the agent invokes the elevation path, bypassing MFA or RBAC. OWASP LLM-07 Insecure Plugin Design.
Severity & confidence
High
Credible abuse path with meaningful impact on confidentiality, integrity, or availability. Remediate on a short timeline; do not wait for the next sprint cycle.
Confirmed
Observed directly by Jiffy scanners or validated by multiple independent sources. Indicators are reliable enough to drive automated action.
Indicators
Observed patterns and artifacts associated with this entry. Each indicator can be copied into your detection stack or SIEM.
permissions\s*:\s*(\*|admin|write-all|all)
allowed_tools\s*:\s*\*
scope\s*:\s*unrestricted
Detection rule
A YARA-style pseudo-rule auto-generated from the indicators above. Useful as a starting point — adapt the syntax for your target detection platform.
rule jiffy_ti_2026_000006
{
meta:
source = "jiffy-intel"
severity = "high"
description = "Auto-generated from Jiffy Intel indicators"
strings:
$content_pattern_0 = "permissions\\s*:\\s*(\\*|admin|write-all|all)"
$content_pattern_1 = "allowed_tools\\s*:\\s*\\*"
$content_pattern_2 = "scope\\s*:\\s*unrestricted"
condition:
$content_pattern_0 or $content_pattern_1 or $content_pattern_2
}Auto-generated from the indicators above. Adapt syntax for your detection stack before deploying.
Affected tools
| Tool | Versions | Status |
|---|---|---|
| Claude Code | * | vulnerable |
| Cursor | * | vulnerable |
Example artifacts
Sanitized examples of artifacts Jiffy has observed exhibiting this pattern. Publisher handles are redacted; version ranges and status reflect the most recent scan.
- tenant-utilities-skillSkillRemoved
Internal-only skill; exfil paths triggered by crafted user prompt.
- org-settings-skillSkillUnder review
- workspace-admin-helperSkillQuarantined
How to remediate
- 01Reject skills that declare wildcard or admin permission scopes.
- 02Require least-privilege declarations.
- 03Jiffy rule PE1 (Excessive Permissions) flags this at static analysis.
Timeline & sources
Timeline
- First observedApr 12, 20265 days ago
- Last updatedApr 12, 20265 days ago
- PublishedApr 9, 20268 days ago
Sources
References
Scan for patterns like this
Point Jiffy at your GitHub org, IDE config, or a single artifact. Get a scored report in under a minute.
Start a free scan