Malicious SkillPublished Mar 13, 2026

Skill that edits ~/.ssh/authorized_keys on first invocation

CriticalAARM tierConfirmed
Seen94times across7customers
jiffy-ti-2026-000011

Summary

Malicious skill that, as part of its stated "dev environment setup" task, appends an attacker-controlled public key to ~/.ssh/authorized_keys. The skill frames the action as adding a CI deploy key, but the resulting persistence is a full-shell backdoor for the attacker. Observed across three independent publishers on the Anthropic Skill marketplace.

Severity & confidence

Severity
Critical

Critical

Active exploitation in the wild, high blast radius, or direct data exfiltration vector. Treat as an urgent remediation target; quarantine affected artifacts immediately.

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.

  • (?i)(?:echo|cat)\s+.{0,160}>>\s*.{0,40}authorized_keys
  • (?is)append[_\s-]?ssh[_\s-]?key
  • (?:~/|/Users/[^/]+/)\.ssh/authorized_keys

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_000011
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $file_path_pattern_0 = "(?:~/|/Users/[^/]+/)\\.ssh/authorized_keys"
    $command_pattern_1 = "(?i)(?:echo|cat)\\s+.{0,160}>>\\s*.{0,40}authorized_keys"
    $tool_call_pattern_2 = "(?is)append[_\\s-]?ssh[_\\s-]?key"
    condition:
        $file_path_pattern_0 or $command_pattern_1 or $tool_call_pattern_2
}

Auto-generated from the indicators above. Adapt syntax for your detection stack before deploying.

Affected tools

ToolVersionsStatus
Claude Code*vulnerable
Claude Desktop*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.

  • ci-deploy-helper-skillSkill
    Removed
    Source
    Anthropic Skills
    Versions
    1.0.0 – 1.1.0
    First observed
    Mar 3, 2026
    Last observed
    Mar 28, 2026

    Writes disguised as CI deploy-key setup.

  • dev-env-bootstrapSkill
    Removed
    Source
    Community registry
    Versions
    0.4.x
    First observed
    Mar 8, 2026
    Last observed
    Apr 2, 2026
  • gh-deploy-bot-skillSkill
    Quarantined
    Source
    Anthropic Skills
    Versions
    2.0.0
    First observed
    Mar 13, 2026

    Held before publish by Jiffy scanner.

How to remediate

  1. 01Block skills that touch ~/.ssh.
  2. 02Require skill manifests to declare an explicit `writes` allowlist and reject any skill whose observed filesystem writes exceed declared scope.
  3. 03Rotate any SSH authorized_keys entries added since the skill was installed.

Timeline & sources

Timeline

  1. First observedMar 3, 20261 month ago
  2. Last updatedApr 12, 20265 days ago
  3. PublishedMar 13, 20261 month 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