The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands to perform linting, type-checking, and testing (e.g., npm test, pnpm test, tsc, eslint). Running npm test on an untrusted repository can lead to arbitrary code execution via malicious scripts defined in package.json. Additionally, the skill references internal scripts scripts/resolve_style_guides.py and scripts/validate_trigger_matrix_sync.py that are not present in the provided files.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes external, potentially untrusted code artifacts.
Ingestion points: Files with extensions .ts, .tsx, .d.ts, and tsconfig*.json as defined in SKILL.md and references/trigger-matrix.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in the processed data were found.
Capability inventory: Shell command execution capabilities including npm, pnpm, tsc, eslint, and python3.
Sanitization: There is no evidence of sanitization or filtering of the content from the ingested files before they are used in command-line operations.

typescript-style-guide