The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local JavaScript analyzer using the Bash tool. The command node ${CLAUDE_PLUGIN_ROOT}/src/claudemd-analyzer.js "${CWD}" runs a script provided within the skill's own environment to process the current working directory.
[INDIRECT_PROMPT_INJECTION]: The skill processes CLAUDE.md files, which are external data sources that could potentially contain malicious instructions intended to influence the agent's behavior during analysis.
Ingestion points: The skill reads project files (specifically CLAUDE.md) in the user's current working directory (${CWD}) via the analyzer script.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential instructions embedded within the analyzed files.
Capability inventory: The skill utilizes the Bash and Read tools, and suggests the use of an Edit tool to modify files based on its findings.
Sanitization: The instructions do not mention any sanitization or validation of the content read from the CLAUDE.md files before processing.

cco-claudemd