to-markdown
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the user and external files to generate its output documents.
- Ingestion points: The skill reads the 'current discussion' and any 'referenced code or documents' to gather content for the Markdown file.
- Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions contained within the ingested data.
- Capability inventory: The skill has the capability to write files to the local file system (defaulting to
docs/explanations/). - Sanitization: There is no requirement or logic specified to sanitize, escape, or validate the content before it is written to the destination file.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install a third-party dependency for visual rendering.
- Evidence: The skill recommends running
npx skills@latest add humanlayer/skills --skill show-meif the dependency is missing, referencing an external repository on GitHub.
Audit Metadata