to-md
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided discussion content to generate standalone Markdown documents, creating a surface for indirect prompt injection.
- Ingestion points: Ingests the 'current discussion' or a 'user-specified topic' to derive document content as described in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore potentially malicious embedded commands within the conversation history.
- Capability inventory: The skill has permissions to read and write files to the local filesystem and create directories (SKILL.md).
- Sanitization: No sanitization process is described for the content being written to the Markdown files.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of an external plugin if visual capabilities are needed.
- Evidence: The skill provides a command to install the 'show-me' skill:
npx skills@latest add humanlayer/skills --skill show-mein SKILL.md.
Audit Metadata