The Agent Skills Directory

[SAFE]: The skill's instructions and code examples align with its stated purpose of assisting in MCP server development. No evidence of prompt injection, data exfiltration, or malicious persistence was found.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface common to developer agents that process external data, though no specific vulnerability was detected.
Ingestion points: The agent reads project files and execution logs using file system operations and bash commands as part of its development workflow (SKILL.md).
Boundary markers: Absent; there are no specific instructions to use delimiters or ignore embedded instructions when reading external files.
Capability inventory: The agent utilizes bash for command execution, git for version control, and standard file operations (SKILL.md).
Sanitization: No explicit sanitization or validation of ingested content is specified in the instructions.

mcp-builder