The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources to perform its analysis and generate documents.
Ingestion points: The skill reads from user-supplied $ARGUMENTS, research.md files, and existing project .md documents found via Grep and Glob tools.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands were found when interpolating external file content into the agent's context for STREAM analysis or PRD generation.
Capability inventory: The skill utilizes Write and Edit tools to create a detailed PRD (docs/prd.md) and uses Bash for searching local files.
Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from external files or user arguments before processing.
[COMMAND_EXECUTION]: The skill instructs the agent to use Grep (typically via the Bash tool) to search for keywords provided in the $ARGUMENTS field. If the user-supplied keywords contain shell metacharacters and the agent does not properly escape them, it could lead to unauthorized command execution within the project environment.

solo-validate