emdash-cli
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx emdash, which downloads and executes theemdashpackage from the npm registry. - [COMMAND_EXECUTION]: The skill relies on executing shell commands for content CRUD operations, schema management, and site data transfers (e.g.,
npx emdash content create,npx emdash schema delete,npx emdash site export). - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests data from external CMS instances and local files.
- Ingestion points: Data is brought into the agent's context through commands like
npx emdash content get,npx emdash media list, andnpx emdash site import --analyze(SKILL.md). - Boundary markers: The instructions do not specify explicit boundary markers or "ignore instructions" warnings when processing the retrieved content.
- Capability inventory: The skill has extensive write capabilities, including
content create/update,schema create/delete, andmedia upload(SKILL.md). - Sanitization: The skill describes a conversion process between Portable Text (JSON) and Markdown in
EDITING-FLOW.md, which provides some structural mapping but is intended for format conversion rather than security sanitization.
Audit Metadata