The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard command-line tools including pnpm audit and jq to analyze dependency metadata. These operations are restricted to the local development environment and serve the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which introduces a surface for indirect prompt injection. Ingestion points: The skill reads package.json and parses the JSON output of pnpm audit. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted data or to ignore embedded instructions. Capability inventory: The skill executes local shell scripts, runs package manager commands, and writes report files to the project repository. Sanitization: There is no mention of sanitizing or validating the contents of the audited packages or the results from the audit tool.
[SAFE]: The skill is designed for auditing and reporting on software dependencies. It follows established development practices and does not exhibit signs of data exfiltration, unauthorized persistence, or obfuscation.

frontend-review-deps