The Agent Skills Directory

[DATA_EXFILTRATION]: Uses curl and specialized tools to fetch content from arbitrary external URLs provided by the user for processing.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install external packages from public registries if not present, including @mozilla/readability-cli (an official Mozilla tool), reader-cli, and the trafilatura Python library.
[COMMAND_EXECUTION]: Employs shell commands (mv, tr, sed) and dynamic Python scripts (python3 -c) to parse HTML data, extract metadata, and manage the resulting text files.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted data from the web.
Ingestion points: External web content retrieved from URLs provided at runtime (SKILL.md).
Boundary markers: Absent; the skill does not use delimiters or warnings to prevent the agent from obeying instructions embedded within the fetched article content.
Capability inventory: The skill has access to the Bash tool (for command execution and script running) and the Write tool (for file creation).
Sanitization: Filenames are sanitized for filesystem compatibility, but the article content is not validated or sanitized before being saved or displayed to the user.

article