Prompt Injection PatternPublished Apr 7, 2026

Instruction override in tool-output markdown tables

HighAARM tierConfirmed
Seen421times across19customers
jiffy-ti-2026-000004

Summary

Attacker embeds hidden instructions in markdown table cells returned by a legitimate-looking tool. Agent reads the tool output and is redirected to execute a secondary task. OWASP LLM-01 Direct/Indirect Prompt Injection.

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.

  • <\!--.*(ignore|override|system|inject).*-->
  • \|\s*ignore previous\s*\|
  • \[system\].*new instructions

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_000004
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "<\\!--.*(ignore|override|system|inject).*-->"
    $content_pattern_1 = "\\|\\s*ignore previous\\s*\\|"
    $content_pattern_2 = "\\[system\\].*new instructions"
    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
Codex*vulnerable
Windsurf*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.

  • slack-search-mcpMCP server
    Under review
    Source
    MCP Registry
    Versions
    0.3.0 – 0.4.1
    First observed
    Mar 12, 2026

    Attack is in data returned by the server, not the server code itself.

  • jira-query-mcpMCP server
    Still live
    Source
    MCP Registry
    Versions
    0.2.x
    First observed
    Mar 19, 2026

    Legitimate server; exploited as an injection vector via ticket-description content.

  • confluence-reader-mcpMCP server
    Still live
    Source
    MCP Registry
    Versions
    1.0.0
    First observed
    Mar 25, 2026

How to remediate

  1. 01Require agent skills to sanitize tool outputs before reading.
  2. 02Strip HTML comments and suspicious instruction phrases.
  3. 03Layer 3 semantic analysis flags these patterns (Jiffy rule PI-001).

Timeline & sources

Timeline

  1. First observedApr 12, 20265 days ago
  2. Last updatedApr 12, 20265 days ago
  3. PublishedApr 7, 202610 days ago

Sources

curatedexternal_partner

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