The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and installs a CLI tool from the vendor's official GitHub repository (github.com/mvanhorn/printing-press-library) and NPM package (@mvanhorn/printing-press-library).
[REMOTE_CODE_EXECUTION]: The skill utilizes go install and npx commands to download and install executable code from the vendor's infrastructure.
[COMMAND_EXECUTION]: The skill executes the archive-is-pp-cli binary to perform web archiving, lookups, and article text extraction.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary external URLs, creating a vulnerability surface for instructions embedded in the retrieved text.
Ingestion points: External URLs provided as arguments to the read, get, tldr, and bulk commands in SKILL.md.
Boundary markers: The skill does not define boundary markers or specific instructions to ignore embedded prompts within the fetched article content.
Capability inventory: The skill uses the Read Bash tool to execute a CLI that performs network operations and local file operations (via the sync and deliver features).
Sanitization: While the tool extracts text from HTML, the skill does not provide mechanisms to sanitize or filter potential prompt injection instructions contained within the retrieved article data.

pp-archive-is