The Agent Skills Directory

[SAFE]: The skill's instructions and configuration do not exhibit any malicious patterns or security risks. It follows a structured workflow using internal platform tools and sub-agents.\n- [DATA_EXFILTRATION]: File access is restricted to the local exploration/ project directory for reading plans and writing notes, which is consistent with the skill's purpose. No unauthorized data access or network transmission patterns were found.\n- [PROMPT_INJECTION]: The skill ingests data from external Markdown files in the exploration/discovery-plans/ directory, which presents an indirect prompt injection surface.\n
Ingestion points: Reads .md files in exploration/discovery-plans/ (SKILL.md).\n
Boundary markers: No explicit delimiters or instructions are used to separate the plan content from the agent's logic.\n
Capability inventory: The skill has access to Bash, Read, and Write tools (SKILL.md frontmatter).\n
Sanitization: No sanitization or validation of the plan content is performed before it is processed.

prototype-builder