The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The file rules/complexity-breakdown.md includes a shell command to run ./scripts/analyze-codebase.sh. This is a local execution pattern used for codebase analysis, but the referenced script is not included in the skill package.
[PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes user-provided code and architecture for assessment. Evidence Chain: 1. Ingestion points: Reads files and architectural descriptions via the $TARGET variable in rules/complexity-breakdown.md. 2. Boundary markers: Lacks explicit delimiters or instructions to prevent the agent from following commands found within the analyzed code. 3. Capability inventory: Possesses the ability to execute shell scripts and spawn specialized agents. 4. Sanitization: No input sanitization or validation of the ingested code is specified in the instructions.

assess