markdown-validation
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses the
npxutility to fetch and execute themarkdownlint-cli2package. It also retrieves a configuration schema from a public GitHub repository. - [COMMAND_EXECUTION]: The
validate-markdown.shscript executes shell commands to run the linting process on local files based on user input. - [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown files which are read by the agent during the validation process. This ingestion of untrusted data lacks boundary markers or sanitization, creating a surface for indirect instructions, though the capability for harm is limited.
- Ingestion points: External markdown files read by the agent as instructed in
SKILL.md. - Boundary markers: None identified in the instructions.
- Capability inventory: Shell script execution and local file modifications.
- Sanitization: No sanitization or validation of the markdown content is performed before processing.
Audit Metadata