The Agent Skills Directory

[SAFE]: The overall logic and tool usage of the skill are consistent with its stated purpose of generating project documentation and implementation plans within a software repository.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted user input via the ${ARGUMENTS} variable.
Ingestion points: User-provided feature descriptions, bug reports, and improvement ideas in SKILL.md.
Boundary markers: The input is enclosed within <feature_description> tags to provide context separation.
Capability inventory: The skill utilizes Bash, Grep, Read, Write, and Edit tools to perform its tasks.
Sanitization: No specific sanitization or filtering of the user input is implemented.
[COMMAND_EXECUTION]: The skill uses Bash and Grep for context gathering during the repo-research-analyst phase. These commands are used locally for repository analysis and do not include patterns for remote code execution or privilege escalation.

medium-plan