The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and instructs the fetching of supplementary instruction sets from ethskills.com and bgipfs.com to provide specialized knowledge for contract auditing and IPFS deployment.
[INDIRECT_PROMPT_INJECTION]: The skill establish an attack surface by instructing the agent to ingest and follow instructions from external markdown files.
Ingestion points: Remote files audit/SKILL.md, qa/SKILL.md from ethskills.com and SKILL.md from bgipfs.com are fetched and processed during development phases.
Boundary markers: No explicit delimiters are defined for interpreting the fetched external content.
Capability inventory: The skill environment supports command execution (yarn, npx, git) and local file system access within the project directory.
Sanitization: The skill assumes the integrity of the ecosystem-specific documentation sources without pre-validation.
[SAFE]: The skill demonstrates a strong security posture by including a dedicated section on credential safety. It provides specific shell commands (grep regex patterns) for the agent or user to identify leaked private keys, API keys, and RPC secrets before committing code. Furthermore, it enforces industry best practices by requiring the use of .env files and .gitignore to manage sensitive project data.

orchestration