The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from CoinMarketCap MCP tools, which represents a potential surface for indirect prompt injection if the API source were compromised.
Ingestion points: External data is ingested in SKILL.md via tools such as get_global_metrics_latest, trending_crypto_narratives, and get_upcoming_macro_events.
Boundary markers: Absent; the skill does not explicitly use delimiters to wrap the tool output in the final report template.
Capability inventory: The skill is limited to read-only API calls and text formatting. It does not have access to the file system, shell execution, or arbitrary network requests.
Sanitization: None specified; the skill relies on the agent's default processing of MCP tool responses.

market-report