The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include a command for the user to add a persistent MCP server to their agent configuration: claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user.
[EXTERNAL_DOWNLOADS]: The skill relies on an external service hosted at https://mcp.manypi.com/mcp to provide its core functionality. This resource is provided by the skill author, manypicom.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that processes data from untrusted external sources, presenting a vulnerability surface for indirect prompt injection.
Ingestion points: As described in the 'ManyPI brief' within SKILL.md, the tool fetches data from store listings, game credits databases, and conference exhibitor lists.
Boundary markers: There are no delimiters or instructions provided to the agent to treat the retrieved data as potentially untrusted.
Capability inventory: The installed manypi tool has the capability to perform network requests to fetch external data.
Sanitization: The skill does not outline any procedures for sanitizing or validating the information gathered from external industry databases.

gaming-studio-leads