Supply ChainPublished Apr 9, 2026

Shadow admin skill: permissive schema grants elevation under prompt injection

HighAARM tierConfirmed
Seen98times across11customers
jiffy-ti-2026-000006

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

Severity
High

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.

Confidence
Confirmed

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.

YARA-style pseudo-rule
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

ToolVersionsStatus
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-skillSkill
    Removed
    Source
    Enterprise private registry
    Versions
    1.4.x
    First observed
    Mar 17, 2026

    Internal-only skill; exfil paths triggered by crafted user prompt.

  • org-settings-skillSkill
    Under review
    Source
    Anthropic Skills
    Versions
    2.0.0
    First observed
    Mar 24, 2026
  • workspace-admin-helperSkill
    Quarantined
    Source
    Community registry
    Versions
    0.9.x
    First observed
    Mar 31, 2026

How to remediate

  1. 01Reject skills that declare wildcard or admin permission scopes.
  2. 02Require least-privilege declarations.
  3. 03Jiffy rule PE1 (Excessive Permissions) flags this at static analysis.

Timeline & sources

Timeline

  1. First observedApr 12, 20265 days ago
  2. Last updatedApr 12, 20265 days ago
  3. PublishedApr 9, 20268 days ago

Sources

scannercurated

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