HighVulnerability

CVE-2026-117558: ai-sdlc plugin MCP server OS command injection via repo argument

Source: NVD(opens in a new tab)
Identifier: CVE-2026-117558
Published: October 27, 2026
Record updated: October 27, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.

Summary

The ai-sdlc plugin MCP server through 0.31.2 contains an OS command injection vulnerability. Attackers can run commands by supplying shell metacharacters in the repo argument, which is interpolated unvalidated into gh issue view or gh pr view commands executed via execSync(). Prompt-injected agents can trigger this, executing commands as the MCP server user.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 7.8(high)
CVSS vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Attack vector: local
Attack complexity: low
Privileges required: low
User interaction: none
EPSS: Not scored. FIRST had not published an EPSS score for this CVE when it was last checked on October 27, 2026.
Disclosure date: October 27, 2026

Weaknesses and techniques

Weakness (CWE): CWE-78
Attack pattern (CAPEC): CAPEC-88
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Plugin
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-117558

First tracked: October 27, 2026 at 02:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items