The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and interprets configuration files from the repository to determine which performance scripts to run. A malicious repository could include instructions or malicious script definitions in these files that might influence the agent's behavior. * Ingestion points: package.json, next.config., lighthouserc., size-limit., bundlesize., webpack.config.*, and repo documentation. * Boundary markers: Absent. The skill does not instruct the agent to ignore or delimit instructions found within the repository files. * Capability inventory: Execution of repository-defined shell scripts using pnpm run. * Sanitization: Absent. There is no logic to validate or sanitize the contents of the scripts before execution.- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through project-defined scripts. While intended for performance profiling, this allows for the execution of arbitrary code if the repository configuration is compromised or malicious.

perf-profiling