The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection to run the command 'cat .ai_state/project.json' at load time. This command retrieves internal project state information into the agent's context.
[PROMPT_INJECTION]: The skill ingests untrusted user requirements through the $ARGUMENTS variable and passes them into a multi-step development process. 1. Ingestion points: The user requirement description in SKILL.md. 2. Boundary markers: No delimiters or boundary instructions are present to isolate user input from the skill's instructions. 3. Capability inventory: The skill can execute shell commands through dynamic context and triggers external development skills. 4. Sanitization: No sanitization or validation of the input string is observed.

vibe-dev