The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and metadata. No executable scripts, binaries, or configuration files that could facilitate code execution were found in the skill bundle.
[SAFE]: All external URL references point to official vendor repositories on GitHub (tenequm) or well-known developer repositories (mattpocock) for licensing and source attribution purposes. These references do not involve any automated downloads or remote code execution.
[PROMPT_INJECTION]: The skill instructs the agent to 'explore the codebase' to answer questions. This creates a surface for indirect prompt injection, where the agent could potentially encounter and follow malicious instructions embedded in codebase comments. However, this is an inherent risk of agentic codebase analysis and is mitigated by the skill's interactive nature and the host agent's safety guardrails.

grill-me