The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands for analyzing project structure. Evidence includes the use of npx madge, pip install pydeps, jdeps, and grep for cycle detection, as well as npx jest --randomize and npx webpack for verification in Step 4.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing and running tools from public package registries. Evidence includes instructions to pip install pydeps and use npx madge, which fetches packages from PyPI and NPM respectively.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes data from untrusted sources. 1. Ingestion points: The agent is instructed to read and trace outputs from Madge, pydeps, and grep, as well as analyze source code files (e.g., src/orders/order.service.ts). 2. Boundary markers: The instructions lack explicit delimiters or warnings to treat tool output or code content as data rather than instructions. 3. Capability inventory: The skill utilizes subprocess execution for package managers and analysis tools. 4. Sanitization: No sanitization or validation of the ingested tool output or source code content is specified.

circular-dependencies