The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple local Go scripts via go run from a relative path (../../scripts/cmd/). These scripts are used for state management, event emitting, and caching throughout the ideation process.
[COMMAND_EXECUTION]: The skill performs automated Git operations (git add and git commit) to persist generated ideation documents to the repository.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its analysis of untrusted project files:
Ingestion points: Reads CLAUDE.md, AGENTS.md, README.md, and directories such as .agents/products/ and docs/product-learnings/ in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed files were identified.
Capability inventory: The skill has the capability to execute shell commands (Go scripts and Git) and write to the file system.
Sanitization: No evidence of sanitization or validation of the content read from the project files before it is used in prompts or command arguments.

product-ideate