The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists of informational guidelines, checklists, and evaluation prompts intended to guide agent reasoning without the use of external scripts, shell commands, or network-enabled tools.
[INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by instructing the agent to ingest external data, though the risk is minimal due to the lack of dangerous capabilities.
Ingestion points: Reads project-specific context files such as .agents/marketing-strategy.md and .agents/marketing-learnings.md, as well as site-level files like llms.txt and robots.txt.
Boundary markers: The instructions do not specify explicit delimiters or guardrails for the ingested content.
Capability inventory: The skill does not utilize any tools for file writing, network exfiltration, or shell execution.
Sanitization: No sanitization or validation logic is defined for the external content it processes.

agent-readiness