The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run npm run build. This action executes scripts defined within the project's package.json file. If the project being analyzed contains malicious build scripts, this could lead to arbitrary command execution on the user's system.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external data (source code and configuration files) which could contain adversarial instructions designed to subvert the agent's behavior.
Ingestion points: The skill reads and greps through project source files (e.g., .ts, .js, .sql) and configuration files (package.json) to identify patterns.
Boundary markers: None identified; the skill does not provide delimiters or instructions to the agent to treat the analyzed content as untrusted data.
Capability inventory: The agent is authorized to execute shell commands such as grep, npm, jq, and cat during the optimization process.
Sanitization: There is no evidence of sanitization or filtering of the analyzed file content before it is processed by the model.

optimize