The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and analyzing project-specific data to generate reviews. Malicious instructions placed within source code or existing documentation could attempt to influence the agent's evaluation or use the agent's write capabilities to modify files inappropriately.
Ingestion points: The skill reads from docs/architecture/**, docs/decisions/**, and src/** (SKILL.md).
Boundary markers: Absent; the instructions do not include delimiters or specific warnings to ignore instructions found within the analyzed files.
Capability inventory: The agent is permitted to use Read, Write, Grep, and Glob tools within the defined project paths.
Sanitization: No sanitization or validation logic is defined for the content extracted from the files before it is processed by the agent.

well-architected