The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted content from multiple project files.
Ingestion points: Project artifacts from directories such as design/, docs/, production/, and src/ are read using Read, Glob, and Grep tools (SKILL.md).
Boundary markers: None identified. The skill does not explicitly use delimiters or instructions to ignore embedded malicious directives in the analyzed content.
Capability inventory: The skill has access to powerful tools including Bash for command execution, Write for file modification, and Task for spawning subagents (SKILL.md).
Sanitization: Absent. Content from project files is processed directly without escaping or validation.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform local validation and administrative tasks.
Evidence: It uses Bash to run test suites and update project status tracking files using shell redirection (SKILL.md).

gate-check