The Agent Skills Directory

[SAFE]: The skill is primarily instructional and does not include executable code, network operations, or access to sensitive system credentials. It operates within the local project documentation scope using standard tools.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it reads and processes external documentation files which could contain malicious instructions.
Ingestion points: SKILL.md instructions to read requirements-{id}.md, technical-review-{id}.md, and program-design-{id}.md.
Boundary markers: Absent; there are no instructions to the agent to distinguish between internal instructions and external data or to use specific delimiters.
Capability inventory: The skill's capabilities are limited to Read, Write, Grep, and Glob, preventing high-impact actions like network exfiltration or shell command execution.
Sanitization: No sanitization or validation of the input document content is specified.

task-breakdown