The Agent Skills Directory

[DATA_EXFILTRATION]: The skill provides a --deliver webhook:<url> feature that allows command output to be POSTed to an arbitrary external URL, which could be used to exfiltrate data if a malicious URL is provided.
[COMMAND_EXECUTION]: The skill instructs the agent to execute the boardgamegeek-pp-cli binary with arguments and subcommands derived from user input, including a natural-language mapping tool (which).
[EXTERNAL_DOWNLOADS]: The skill automates the installation of binaries and dependencies from external sources, specifically using npx for Node.js packages and go install for Go modules hosted on GitHub.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the BoardGameGeek API which could contain untrusted content.
Ingestion points: Data is fetched from the BoardGameGeek XMLAPI2 via commands like thing, collection, and plays in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat API responses as untrusted data.
Capability inventory: The skill has capabilities to execute subprocesses, write to the local file system (--deliver file:), and perform network POST requests (--deliver webhook:).
Sanitization: There is no evidence of sanitization or validation performed on the data returned from the external API before it is processed by the agent.

pp-boardgamegeek