The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local script scripts/find-language-detector-targets.mjs using Node.js to scan the workspace for Language Detector API markers. The script is included in the skill package and restricts its operations to reading file names and checking for specific string patterns within the local directory.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it performs workspace scanning.
Ingestion points: The scripts/find-language-detector-targets.mjs script reads file contents throughout the workspace to identify API markers (Step 1 and Step 5 in SKILL.md).
Boundary markers: None provided for the output of the discovery script.
Capability inventory: The agent can execute shell commands (Node.js) and write files based on its findings.
Sanitization: There is no explicit sanitization or instruction to ignore potentially malicious embedded content within the analyzed workspace files.
[EXTERNAL_DOWNLOADS]: The documentation mentions the @types/dom-chromium-ai package for TypeScript support. This is a standard development dependency for Chromium-based AI APIs and is treated as a safe reference to a well-known package registry.

language-detector-api