The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external content fetched from user-provided URLs.
Ingestion points: The skill uses curl and trafilatura to fetch and parse external websites and GitHub READMEs (SKILL.md).
Boundary markers: There are no explicit instructions to the AI to ignore instructions found within the fetched content or use specific delimiters.
Capability inventory: The skill uses the Bash tool to execute curl and uvx trafilatura, bringing external data into the agent context (SKILL.md).
Sanitization: No explicit sanitization or filtering of the fetched content is described.
[COMMAND_EXECUTION]: The skill instructs the agent to execute bash commands to extract data.
Evidence: Uses curl -fsSL "<URL>" | uvx trafilatura --recall --output-format markdown to fetch and process external content (SKILL.md).
[EXTERNAL_DOWNLOADS]: The skill fetches content from external sources at runtime.
Evidence: Fetches Markdown files from raw.githubusercontent.com and other web content using curl (SKILL.md).

write-social-post