The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to process and upload files using the npx utility.
Evidence: Invokes npx @tentagrip/seemd <path-to-md-file>.
Evidence: Includes a secondary execution path rtk proxy npx -y @tentagrip/seemd for environments with tool wrappers.
[EXTERNAL_DOWNLOADS]: The skill downloads and executes a package from a public registry at runtime.
Evidence: Uses npx to fetch the @tentagrip/seemd package from the npm registry.
[DATA_EXFILTRATION]: The skill's primary function is to send local file content to an external web service.
Evidence: Uploads the targeted .md file and any linked local documents to https://seemd.xyz to generate public URLs.
[PROMPT_INJECTION]: The instructions include directives to suppress specific operational details from the user and create a surface for indirect instructions.
Evidence: Explicitly instructs the agent to avoid mentioning data expiry or upload summaries to the user.
Ingestion points: The skill reads and processes local markdown files (SKILL.md).
Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the processed markdown content.
Capability inventory: The skill has the ability to execute shell commands and perform network operations via the npx tool (SKILL.md).
Sanitization: No sanitization or validation of the content within the uploaded markdown files is specified before processing.

seemd