The Agent Skills Directory

[PROMPT_INJECTION]: The skill interpolates user-supplied data such as feature_description and tech_stack directly into the prompts for sub-agents. This creates a surface for indirect prompt injection where malicious input could influence the behavior of the research agents.
Ingestion points: Inputs feature_description and tech_stack are defined in SKILL.md and used across various tasks.
Boundary markers: The skill does not employ explicit delimiters or instructions to ignore embedded commands within the interpolated variables.
Capability inventory: The skill spawns multiple sub-agents (e.g., git-researcher, docs-researcher) and dynamically injects skills from the coding_styles array.
Sanitization: No sanitization or validation of the input strings is performed before interpolation.
[COMMAND_EXECUTION]: The skill utilizes internal vendor-defined agents (majestic-engineer:*) to perform repository analysis and git-related research. These operations are scoped to the project environment and are consistent with the skill's stated purpose.
[EXTERNAL_DOWNLOADS]: The workflow includes a conditional external research phase where agents like docs-researcher may access network resources to retrieve technical documentation. These operations are handled by internal vendor sub-agents.

blueprint-research