AGENT LAB: SKILLS

azure-devops

Fail

Audited by Snyk on Feb 19, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill includes examples that encode and place PATs directly into Authorization headers and shell commands (e.g., curl with base64-encoded :YOUR_PAT), which instructs embedding secrets verbatim in outputs and therefore creates an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's core workflow and SKILL.md explicitly include API calls that fetch user-generated Azure DevOps content—e.g., GET /{organization}/{project}/_apis/git/repositories/.../items?download=true (file contents), GET .../pullrequests/{pullRequestId}/threads (PR comments/threads), and GET .../wiki/wikis/{wikiId}/pages (wiki pages)—which the agent would ingest and could allow instructions in that third‑party content to materially influence subsequent tool actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 19, 2026, 03:23 PM