The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and act upon briefings from external Sitefire services, which may contain adversarial instructions targeting the agent.
Ingestion points: The agent ingests data through the list_actions and get_briefing tools as specified in the workflow section of SKILL.md.
Boundary markers: There are no specific instructions or delimiters provided to help the agent isolate external briefing data from its core operational instructions.
Capability inventory: The agent is authorized to call the write_article tool, interact with email composition tools for outreach, and modify existing content based on the recommendations found in the briefings.
Sanitization: The skill does not describe any mechanisms for validating, escaping, or filtering the content retrieved from the external API before the agent processes and acts upon it.

sitefire-actions