Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
68
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The skill's examples and auth instructions show embedding API tokens/headers and plaintext secrets directly into CLI flags and environment variables (and persisting them), which requires the agent to handle and potentially output secret values verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
The EmDash CLI remote command workflow ingests outsider-authored content when you run commands like `npx emdash content get ...` (and likely `search`/`types`/`schema`/`media`), which fetch data from a configured EmDash instance URL over HTTP and then convert/return any stored Portable Text/markdown (i.e., attacker-controlled CMS content becomes LLM-readable text at runtime).
1717d31
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.