The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion of untrusted external data.
Ingestion points: According to SKILL.md, the agent processes 'Accepted Research, Brief, and Writer Results' as well as 'current SERP/competitor evidence'.
Boundary markers: There are no instructions or delimiters (such as XML tags or triple quotes) defined to isolate these external inputs from the agent's core instructions.
Capability inventory: The agent has the capability to write local files (report.json) and execute content updates via the dineway content update tool.
Sanitization: The instructions do not specify any validation, filtering, or escaping of the ingested external content before it is used to generate optimization suggestions.
[COMMAND_EXECUTION]: The skill utilizes vendor-specific command-line tools to perform its primary function.
Tooling: SKILL.md instructs the agent to execute dineway content update --draft --rev <current-revision> to apply changes. While these are recognized vendor resources for 'dineway', they represent the mechanism through which injected instructions could manifest as unauthorized content modifications.

dineway-content-optimize