The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external technical documentation, architecture diagrams, and source code repositories (e.g., docs/architecture.md, infrastructure manifests, penetration test reports).
Ingestion points: The skill ingests various external files and repositories as primary inputs for its security review and threat modeling process.
Capability inventory: The skill is configured with Read, Write, and Grep tools. It does not possess network access or the ability to execute arbitrary code or subprocesses.
Boundary markers: The instructions do not define specific delimiters or instructions to the agent to disregard potential instructions embedded within the analyzed data.
Sanitization: The skill lacks explicit sanitization or filtering logic for content extracted from external documents before it is processed by the agent's logic.

bmad-security-review