The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze arbitrary content from a local repository, including code, tests, and documentation. This creates an attack surface where malicious instructions embedded in the repository's files could influence the agent's behavior.
Ingestion points: The skill reads files from src/, tests/, hooks/, assets/, and documentation such as AGENTS.md and REVIEW.md in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the content of the files being analyzed and its own operational instructions.
Capability inventory: The skill utilizes shell commands like rg (ripgrep) and build/test tools such as bun run check, knip, and jscpd as specified in SKILL.md.
Sanitization: No sanitization or validation of the ingested content is performed before processing.
[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands and development tools to perform its analysis.
Evidence: In SKILL.md, the agent is directed to use rg (ripgrep) for searching across the repository and to run bun run check for validating implementations. These commands execute logic and scripts defined within the repository's environment.

ccsn-find-simplifications