The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including bunx markdownlint-cli and a local synchronization script ./scripts/validate-skill-sync.sh to perform file validation tasks.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the bunx package runner to execute markdownlint-cli, which may involve downloading the package from the public npm registry (a well-known service).\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and validate the contents of other SKILL.md and reference markdown files.\n
Ingestion points: Reads contents from SKILL.md and references/*.md files within the workspace.\n
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands within the files being validated.\n
Capability inventory: The agent possesses the capability to execute shell commands and run local scripts while performing these validations.\n
Sanitization: Absent; the skill does not specify any sanitization, filtering, or escaping logic for the content of the files before processing.

skill-validator