The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-supplied idea descriptions and responses to clarification questions, which are then used in research and file generation.
Ingestion points: Processes $ARGUMENTS and responses from AskUserQuestion within the 5-phase pipeline defined in SKILL.md.
Boundary markers: The skill does not employ specific delimiters or "ignore instructions" markers when interpolating user data into subsequent prompts or markdown files.
Capability inventory: The skill has the capability to write files (idea.md, validate.md, README.md) and perform Git operations including commit and push.
Sanitization: No explicit sanitization, filtering, or escaping of user-supplied content is performed before interpolation.
[COMMAND_EXECUTION]: The skill executes shell commands to maintain repository synchronization and manage project files.
Evidence: Instructions in SKILL.md direct the agent to execute git rev-parse, git fetch, git pull --rebase, git stash, and git push to sync with the remote repository.
Evidence: The skill reads and writes configuration files in the user's home directory at ~/.config/ideas-root.txt and ~/.openclaw/ideas-root.txt to resolve storage paths.

idea-validator