The Agent Skills Directory

[SAFE]: The skill's primary purpose is codebase and market research. It provides structured guidance for an agent to identify data schemas, API routes, and content types within a project to suggest SEO strategies.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it processes untrusted data from the local codebase (e.g., JSON, CSV, MDX files) and external web content (via WebSearch and WebFetch). While this is inherent to its discovery function, it is documented as a risk factor.
Ingestion points: Codebase files explored via Read, Glob, and Grep tools; external search results and web pages retrieved via WebSearch and WebFetch tools.
Boundary markers: The instructions do not explicitly require the use of delimiters or 'ignore instructions' blocks when processing ingested data.
Capability inventory: The skill utilizes Bash, Read, and WebFetch, which allow for significant data interaction.
Sanitization: There is no mention of sanitizing or escaping the data retrieved from external sources before it is analyzed by the agent.

pseo-discovery