The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard pnpm commands (generate, build, test, dev) to facilitate a legitimate plugin migration workflow within the author's monorepo environment. These commands are expected for the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process files from external plugin repositories during the migration process.
Ingestion points: The agent reads and copies files such as package.json, README.md, and configuration files from the plugin being migrated (referenced in SKILL.md).
Boundary markers: No specific boundary markers or instructions to ignore embedded content are defined for the files being migrated.
Capability inventory: The skill possesses capabilities to write files to the local system (test-studio wiring, README updates) and execute shell commands (pnpm build/test).
Sanitization: No sanitization or validation of the content within the migrated files is explicitly mentioned.
Note: This represents a standard risk surface inherent to plugin migration tasks; no malicious patterns were detected.

plugin-transfer