The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash to perform local discovery of research-related files using find and grep. These operations are scoped to the project directory and intended for identifying artifacts like personas, JTBD frameworks, and interview notes.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes user-controlled markdown files to generate summaries and quality assessments.
Ingestion points: Local markdown files (*.md) discovered during the environment scan.
Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are used when reading file content.
Capability inventory: The agent has access to Bash, WebFetch, WebSearch, and Read tools.
Sanitization: The instructions do not define sanitization or validation steps for the content retrieved from the research artifacts before it is processed by the agent.
[SAFE]: The external references and repository URLs are consistent with the verified author 'tonone-ai'. Although there is a version mismatch between the skill manifest and the plugin configuration, it does not pose a security risk.

echo-recon