The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown instructions defining a development process. It does not contain scripts, configuration files, or executable payloads.- [INDIRECT_PROMPT_INJECTION]: The workflow involves processing external data (a "plan" containing Acceptance Criteria and Verification Plans). While this presents a surface where malicious instructions could be embedded in the input data, the skill's requirement for a specific mapping between criteria, oracles, and test cycles provides a structured framework that mitigates the risk of unintended behavior by enforcing rigorous verification steps.- [SAFE]: The instructions promote best practices such as separate commits for refactors and baseline testing. There are no patterns suggesting data exfiltration, obfuscation, or privilege escalation.

implement-plan