chunk-markdown
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted Markdown files and possesses the capability to write new files to the system, creating a vulnerability surface for indirect prompt injection. * Ingestion points: The user-provided Markdown file path. * Boundary markers: There are no explicit instructions to the agent to treat the Markdown content as data only or to ignore embedded instructions. * Capability inventory: The skill is instructed to read files, create directories, and write multiple Markdown files. * Sanitization: The instructions specify that output slugs should be sanitized.
- [COMMAND_EXECUTION]: The procedure requires the agent to perform file system operations including directory creation (mkdir) and file writing.
Audit Metadata