The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and potentially fetches markdown examples from an untrusted GitHub repository (https://raw.githubusercontent.com/jhauga/tldr/...) to use as stylistic references for generating documentation. These files are provided as examples for the agent to understand the target format.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from arbitrary documentation URLs provided by the user using the #fetch tool. It lacks explicit instructions to ignore or sanitize potentially malicious commands or instructions that could be embedded within the external documentation it retrieves.
Ingestion points: Processes content from user-provided URLs and context files (SKILL.md).
Boundary markers: The skill defines a strict markdown template for output but does not provide delimiters or instructions to the agent to treat fetched content as data only.
Capability inventory: The skill leverages the platform's #fetch tool and generates markdown text based on retrieved content.
Sanitization: There is no evidence of input validation, filtering, or escaping for the data fetched from external sources.

create-tldr-page