The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by fetching URLs via WebFetch and reading files such as API specifications, DB schemas, and design documents.
Ingestion points: SKILL.md Phase 1 specifies reading external docs via WebFetch and reading various input files (--api, --schema, --docs).
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the external data are present.
Capability inventory: The skill has the capability to write files (Write tool used in Phases 3, 4, and 5) and interact with the user via AskUserQuestion.
Sanitization: No evidence of sanitization or validation of the fetched external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill identifies WebFetch as a tool to retrieve documentation, wikis, or READMEs from external URLs provided by the user.
[COMMAND_EXECUTION]: The skill includes logic to automatically trigger and execute the /dev-scout skill workflow if the scout.md file is missing for a feature, representing automated tool invocation.

dev-specs