The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of the hackernews-pp-cli and hackernews-pp-mcp binaries via the shell to interact with Hacker News data.
[EXTERNAL_DOWNLOADS]: Installs the required binaries from the author's public repositories using npx (@mvanhorn/printing-press) and go install (github.com/mvanhorn/printing-press-library).
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag and a feedback command that can transmit command results or feedback to external endpoints. While designed for data routing, this capability could be used to send information to unauthorized third-party servers.
[PROMPT_INJECTION]: The skill ingests untrusted content from the Hacker News API (stories and comments), which introduces a surface for indirect prompt injection. A malicious post on Hacker News could contain instructions meant to influence the agent's behavior.
Ingestion points: Commands such as stories, items, and search (in SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded content are implemented.
Capability inventory: Shell command execution and network delivery via webhooks.
Sanitization: No sanitization of the retrieved content is mentioned before it is processed by the agent.

pp-hackernews