The Agent Skills Directory

[SAFE]: No malicious behavior or high-risk security patterns were detected. The skill is designed for documentation and code analysis within a trusted local environment.- [DATA_EXFILTRATION]: The skill accesses local project files, specifically .eo-project.json and various documentation files within the eo-doc/ directory. This access is necessary for the skill's diagnostic function and does not include access to sensitive system directories or external network endpoints.- [PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection by processing external project documentation.
Ingestion points: The skill reads eo-doc/dev/INDEX.md, spec.md, change.md, and state/INDEX.md.
Boundary markers: There are no explicit markers or instructions used to prevent the agent from following potential commands embedded within the documentation files.
Capability inventory: The skill possesses no capabilities for command execution, file writing, or network operations, limiting the potential impact of any indirect injection.
Sanitization: Content from documentation files is not sanitized before being processed by the agent.

eo-fix