intomd
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch content fromhttps://into.md/, a third-party Markdown conversion service. This dependency on an external service means the agent's input (the target URL) is transmitted to a third party. - [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: The skill accepts a user-provided URL via the
$1parameter inSKILL.mdand fetches its content. - Boundary markers: No delimiters or instructions are used to prevent the agent from obeying instructions embedded in the fetched Markdown content.
- Capability inventory: The skill possesses network read capabilities via
curl. - Sanitization: There is no sanitization or validation of the fetched content before it is returned to the agent's context.
Audit Metadata