The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a workflow that relies on instructions found in docs/PLAN.md and docs/TODO.md. This creates an attack surface for indirect prompt injection if these files are manipulated to include malicious directives.
Ingestion points: Processes docs/PLAN.md and docs/TODO.md from the project directory (SKILL.md).
Boundary markers: Lacks delimiters or instructions to treat data in project files as non-executable text.
Capability inventory: Possesses file-writing and code implementation capabilities across the project directory.
Sanitization: No sanitization or validation of documentation content is performed before execution.

go-project