The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the judge-me-pp-cli binary using npx from the @mvanhorn/printing-press-library package and via go install from the mvanhorn/printing-press-library GitHub repository. These sources are linked to the tool's development infrastructure.
[COMMAND_EXECUTION]: The skill is designed to execute the judge-me-pp-cli binary with various flags and subcommands to manage store reviews, settings, and webhooks.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of product reviews retrieved from the Judge.me API. The instructions explicitly warn that raw review information is not sanitized, which could allow malicious instructions embedded in reviews to influence the agent's behavior.
Ingestion points: Data retrieved via judge-me-pp-cli reviews index and judge-me-pp-cli reviews get as documented in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded content are provided in the skill instructions.
Capability inventory: The CLI tool possesses capabilities for file system writes (--deliver file:<path>), network requests (--deliver webhook:<url>), and general CLI command execution as listed in SKILL.md.
Sanitization: The skill specifically notes that review content is not sanitized and may contain XSS or other risks.

pp-judge-me