The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like grep, ls, and git log to find and analyze relevant source files in the codebase.
[COMMAND_EXECUTION]: The skill writes updated YAML definitions to the .flowchad/flows/ directory on the local filesystem.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted data from the codebase to drive its logic.
Ingestion points: Reads content from source files (e.g., .tsx, .jsx, .rb) located in src/, app/, components/, and views/ as described in SKILL.md.
Boundary markers: Absent. The skill does not define specific delimiters to separate code content from instructions during the drafting phase.
Capability inventory: File read access (via grep and ls) and file write access to the specific .flowchad/flows/ directory.
Sanitization: Absent. The skill does not specify any validation or filtering of the code content before it is interpreted to update flow steps and expectations.

flow-update