leetcode-coach
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the '@tiny-fish/cli' global npm package, which is a verified resource from the authoring vendor.
- [COMMAND_EXECUTION]: Employs shell commands to verify the local environment, manage authentication, and invoke the 'tinyfish' CLI to run scraping agents on third-party URLs.
- [PROMPT_INJECTION]: The skill processes untrusted data from external coding platforms and writes it to the local filesystem, which constitutes an indirect prompt injection vulnerability surface.
- Ingestion points: External problem descriptions and metadata are fetched from LeetCode, HackerRank, and Codeforces URLs via the 'tinyfish agent run' command (SKILL.md).
- Boundary markers: Instructions do not include specific delimiters or warnings to ignore potentially malicious embedded instructions within the scraped content.
- Capability inventory: The skill is designed to write multiple files (problem.md, solution.{ext}, test_cases.md) to the current working directory and execute shell commands via the CLI (SKILL.md).
- Sanitization: There is no evidence of validation or sanitization performed on the fetched external data before it is written to the local filesystem.
Audit Metadata