CtrlK
BlogDocsLog inGet started
Tessl Logo

adobe/aem-edge-delivery-services

Skills for building AEM Edge Delivery Services sites — block development, content modeling, code review, testing, and page import.

82

1.04x
Quality

76%

Does it follow best practices?

Impact

88%

1.04x

Average score across 6 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Security

1 medium severity finding. This skill can be installed but you should review these findings before use.

Medium

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

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes untrusted, user-generated content—GitHub PR diffs, PR comments (see SKILL.md "For PR Review" with gh api/gh pr view calls and the "External Content Safety" note) and arbitrary public preview URLs/screenshots (see scripts/capture-screenshots.js which visits preview URLs)—and uses that content to drive review decisions and generate GitHub suggestions, so third-party content can materially influence agent actions.

Report incorrect finding
Audited
Security analysis
Snyk