The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the food52-pp-cli and food52-pp-mcp binaries from the author's GitHub repository and the npm package registry.
[COMMAND_EXECUTION]: Instructions guide the agent to perform installation using npx and go install to prepare the skill's environment.
[DATA_EXFILTRATION]: The tool includes a --deliver webhook:<url> flag, which allows the agent to POST command results to an external URL. A feedback mechanism is also present that can be configured to send local data to a remote endpoint via the FOOD52_FEEDBACK_ENDPOINT environment variable.
[INDIRECT_PROMPT_INJECTION]: The skill ingests recipe and article data from Food52, which could serve as a vector for indirect prompt injection if external content contains malicious instructions.
Ingestion points: Data retrieved via recipes search, recipes get, articles browse, and articles get (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are present in the provided documentation.
Capability inventory: The skill uses the Bash tool and has the ability to write files and perform network requests (via webhooks).
Sanitization: No specific sanitization or validation logic for the ingested Food52 content is described.

pp-food52