The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze external project descriptions or requirement briefs, which are untrusted data sources. This creates a surface for indirect prompt injection where instructions embedded in the input documents could influence the agent's behavior or be persisted into the generated .stitch/SITE.md file.
Ingestion points: The skill uses Read and web_fetch to ingest project descriptions and requirements briefs from local files or web sources.
Boundary markers: No specific boundary markers or instructions to treat external data as untrusted are provided.
Capability inventory: The skill possesses file system access via Read and Write, and network access via web_fetch tools.
Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the external content before it is processed or written to the output file.

site-md