convert-to-markdown
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill contains a command to install the
ezycopyCLI by downloading a script from the author's GitHub repository and executing it via a shell pipe (curl | sh). This resource originates from the skill's author and is used for initial setup.\n- [EXTERNAL_DOWNLOADS]: The skill references an installation script hosted on the author's repository atgithub.com/gupsammy/EzyCopy.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs, which creates an attack surface for indirect prompt injection. \n - Ingestion points: External web content is retrieved from URLs provided by the user using the
ezycopycommand as described inSKILL.md.\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched markdown content.\n
- Capability inventory: The skill uses the
Bashtool to executeezycopyandcurlcommands.\n - Sanitization: No explicit sanitization or filtering of the retrieved web content is performed by the skill before presenting it to the agent.
Audit Metadata