The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash and Task tools to execute commands for workspace discovery and rule auditing, which is consistent with its stated purpose of managing configuration files.- [PROMPT_INJECTION]: The skill reads content from various workspace configuration files (such as CLAUDE.md and .cursorrules) that could contain malicious instructions designed to influence the agent's auditing logic.
Ingestion points: All config files found during the discovery phase (Step 1) are processed using Read, Glob, and Grep tools.
Boundary markers: There are no specific instructions or delimiters used to isolate the ingested file content from the agent's own instructional context.
Capability inventory: The skill defines the use of Write, Edit, Bash, and Task tools, which could be misused if the agent obeys instructions found within audited files.
Sanitization: No sanitization or validation logic is present to filter content before it is processed by the agent.

agent-config-audit