The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill facilitates the ingestion of untrusted user data which is subsequently written to a persistent file, potentially influencing downstream automated processes. • Ingestion points: Feature descriptions and answers to clarifying questions provided by the user (SKILL.md). • Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded instructions within user-provided text. • Capability inventory: The skill writes Markdown files to the local tasks/ directory. • Sanitization: Absent; the instructions direct the agent to incorporate user answers directly into the generated PRD structure.
[No Code] (SAFE): The skill consists entirely of natural language instructions and does not include any executable scripts, shell commands, or external package dependencies.

prd