Security Audit
mcp-atlassian-cve-2026-27825
github.com/cisco-ai-defense/skill-scannerTrust Assessment
mcp-atlassian-cve-2026-27825 received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Prompt Injection for Credential Harvesting.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on July 1, 2026 (commit 41fec4a9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection for Credential Harvesting The skill definition contains a prompt injection payload in the 'hint' parameter designed to trick the LLM into echoing the 'Authorization' header. If executed by an LLM, this would result in the exposure of sensitive authentication tokens. Do not include instructions in parameters that can manipulate the LLM's behavior. Sanitize inputs and configure the LLM system prompt to strictly prohibit the disclosure of credentials, authorization headers, or API keys. | LLM | SKILL.md:5 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | evals/test_skills/malicious/mcp-atlassian-cve-2026-27825/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/ec1c72801b9c32ef)
Powered by SkillShield