readme-i18n
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill creates an attack surface for indirect prompt injection by processing untrusted text from files using read and write capabilities.
- Ingestion points: The skill uses
read_fileto ingest content fromREADME.mdandREADME.zh-TW.md, which are untrusted external sources. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the README files being translated.
- Capability inventory: The skill utilizes
replace_string_in_file(filesystem write) andread_file(filesystem read), allowing for modification of the repository content. - Sanitization: No sanitization or filtering is applied to the ingested content before it is processed and written back to the disk.
Audit Metadata