anibon-world-identity
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes several Python scripts (
fetch_fgo_db.py,fetch_pokemon_db.py,fetch_ygo_db.py) designed to bootstrap local SQLite databases by downloading metadata from well-known community APIs and repositories (Atlas Academy, YGOPRODeck, and GitHub). These operations are essential for the skill's primary function and target legitimate data providers. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data through
fetch_story_ref.py(which fetches search engine snippets) andalign_ref_timeline.py(which parses user-provided SRT subtitle files). However, the risk is negligible as the scripts include length constraints on fetched text, and the data is used exclusively for entity name mapping rather than instruction following.
Audit Metadata