The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its repository exploration functionality. * Ingestion points: Step 2 in SKILL.md directs the agent to read relevant files, configuration, and documentation. * Boundary markers: Absent; the skill does not instruct the agent to ignore or delimit instructions found within processed files. * Capability inventory: The skill is primarily instructional and does not contain scripts for subprocess execution or file modification. * Sanitization: No sanitization or validation of the repository content is specified.
[NO_CODE]: The skill consists only of instructional prompts and configuration files, with no executable scripts, binaries, or automated command execution.

grilling-designs