The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions involve executing shell commands using curl, httpie, newman, and npx to interact with APIs and run utility tools for mocking and documentation.
[PRIVILEGE_ESCALATION]: The templates/README.md file recommends using chmod +x to grant execution permissions to the included shell script scripts/curl-examples.sh, which is a standard development practice.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external API responses, creating a potential surface for indirect prompt injection if the agent interprets response content as instructions.
Ingestion points: API response bodies captured via curl, httpie, and axios interceptors, as well as Postman test scripts in templates/postman-collection.json.
Boundary markers: No explicit delimiters are defined to isolate untrusted API data from the agent's internal instructions.
Capability inventory: The skill utilizes shell execution (curl, npx), file output (-o), and network operations.
Sanitization: No specific sanitization or validation of external API content is documented.

api-tools