The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of a CLI tool from external sources. It provides instructions to download code from npm (@mvanhorn/printing-press-library) and GitHub (github.com/mvanhorn/printing-press-library).
[COMMAND_EXECUTION]: The skill's primary function is to execute shell commands using the yeswehack-pp-cli binary. This involves running various subcommands like sync, triage, and report submit via the agent's Bash tool.
[DATA_EXFILTRATION]: The skill documents a --deliver webhook:<url> feature. This capability allows the tool to POST its output (which may include program details, scopes, or report drafts) to any specified external URL.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and incorporates it into the agent's context.
Ingestion points: Data is ingested from the YesWeHack API and public hacktivity feeds (SKILL.md).
Boundary markers: The instructions do not define boundary markers or delimiters for the ingested data.
Capability inventory: The agent has the ability to execute shell commands, write files, and perform network requests via the Bash tool.
Sanitization: There is no mention of sanitizing or filtering external content before it is passed to the agent for synthesis or summarization (e.g., the hacktivity learn recipe).

pp-yeswehack