The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests various external project files to inform its code generation process, creating a potential vulnerability to malicious instructions embedded in those files.
Ingestion points: Reads project configuration (project.yaml), technical preferences, existing test files (tests/**/*_test.*), and design documents (design/gdd/*.md, tr-registry.yaml).
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the content of these files from the agent's core instructions.
Capability inventory: The skill utilizes Read, Glob, Grep, and Write tools to interact with the file system.
Sanitization: No sanitization or validation logic is defined for the content extracted from these files before it is processed.
[DYNAMIC_CONTEXT_INJECTION]: The skill employs dynamic context injection to execute shell commands at load time for environment configuration.
Evidence: The file contains the command !"source "${CLAUDE_PROJECT_DIR:-.}/.claude/hooks/yaml-helper.sh" 2>/dev/null && resolve_config --keys automation" which runs a project-specific script to resolve automation settings when the skill is accessed.

test-helpers