The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content from software registries and changelogs through tools such as get_release and get_catalog_entry. This creates a potential surface for indirect prompt injection, where malicious instructions could be embedded in fetched release notes or documentation. * Ingestion points: External release data fetched via MCP tools. * Boundary markers: None identified in the instructions for separating external content from system instructions. * Capability inventory: The skill performs data synthesis and reporting; no dangerous system-level capabilities are exposed. * Sanitization: No explicit sanitization or filtering of the external data is mandated in the skill instructions.
[NO_CODE]: The skill consists entirely of markdown instructions and does not include any accompanying source code, scripts, or binary files, which significantly reduces the direct attack surface.

releases-mcp