The Agent Skills Directory

[PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by requiring the agent to process and act upon data retrieved from external API endpoints and local repository files.
Ingestion points: API response bodies fetched via curl and file search results produced by grep as specified in the checklist and quick reference sections of SKILL.md.
Boundary markers: Absent. The skill does not provide delimiters or instructions to the agent to treat the ingested command output as data only or to ignore potential instructions embedded within those outputs.
Capability inventory: The skill utilizes curl for network requests to development servers, grep for recursive file system searching, and adb for interacting with Android device logs.
Sanitization: Absent. There is no requirement or instruction to validate or escape the content of API responses or log outputs before the agent uses them for verification.
[COMMAND_EXECUTION]: The skill provides numerous shell commands for the agent to execute to verify implementation status. This includes grep for searching specific PHP controllers in local paths, curl for making authenticated network requests to a local host alias (10.0.2.2), and adb logcat for capturing real-time device logs. While intended for testing, these provide the agent with broad access to the local development environment and system state.

api-testing-verification