hns-oss-docs-i18n-rules
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it instructs the agent to ingest and process external data (READMEs and documentation content) that could contain malicious instructions.
- Ingestion points: Processes project files such as
README.mdand content withindocs-site/content/across multiple locales. - Boundary markers: The instructions do not define delimiters or specific markers to isolate untrusted file content from the agent's core instructions.
- Capability inventory: The skill allows access to
Read,Grep,Glob, andBashtools, which could be abused if an injection is successful. - Sanitization: No sanitization, validation, or escaping of the ingested documentation content is described.
- [SAFE]: No hardcoded credentials or sensitive file path access (e.g., .ssh, .aws) were detected.
- [SAFE]: The skill explicitly instructs the agent not to execute external scripts (
docs-i18n-check.sh,gen_menu.py), recommending inlined checks instead, which reduces the risk of remote code execution. - [SAFE]: All referenced domains (e.g.,
adk.mo.ai.kr) are consistent with the vendor's infrastructure.
Audit Metadata