Prompt Injection PatternPublished Apr 4, 2026

Skill returns large output to push user's prompt out of context

MediumAARM tierConfirmed
Seen18times across3customers
jiffy-ti-2026-000032

Summary

Skill whose output deliberately inflates to tens of thousands of tokens of filler, pushing the user's original prompt out of the model's context window. The injected instructions at the start of the filler become the new "top" of context and drive subsequent behavior.

Severity & confidence

Severity
Medium

Medium

Notable weakness with plausible abuse chains or partial mitigations already in place. Track, and resolve as part of your normal hardening cadence.

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)lorem\s+ipsum[\s\S]{10000,}|(?:placeholder\s+){1000,}

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_000032
{
    meta:
        source = "jiffy-intel"
        severity = "medium"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)lorem\\s+ipsum[\\s\\S]{10000,}|(?:placeholder\\s+){1000,}"
    condition:
        $content_pattern_0
}

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.

  • doc-filler-skillSkill
    Removed
    Source
    Anthropic Skills
    Versions
    1.0.0
    First observed
    Mar 25, 2026
    Last observed
    Apr 12, 2026
  • template-expansion-skillSkill
    Quarantined
    Source
    Community registry
    First observed
    Mar 29, 2026

How to remediate

  1. 01Cap per-tool-call output size.
  2. 02Reject skill output that exceeds a threshold without a compelling reason.

Timeline & sources

Timeline

  1. First observedMar 25, 202623 days ago
  2. Last updatedApr 22, 2026today
  3. PublishedApr 4, 202613 days ago

Sources

curated

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