The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform local codebase analysis, including executing scripts to gather metrics and metadata from the target project. It also defines a PreToolUse hook that executes a local script to load assessment baselines.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the local filesystem during the assessment phase using Read, Grep, and Glob tools. This creates an attack surface where malicious instructions embedded in analyzed files could attempt to influence the agent's behavior. The skill mitigates this risk by implementing file sampling limits (MAX 30 files) and delegating evaluation tasks to sub-agents with constrained prompts and specific scope instructions.

assess