hns-oss-docs-readme-sync
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
grepcommands viaBashto perform structural verification on markdown files, including counting headers, checking table structures, and ensuring code block parity.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and translate content from external markdown files, which presents a surface for potential indirect prompt injection attacks.\n - Ingestion points: Reads content from
README.ko.md,README.md,README.ja.md, andREADME.zh.mdat the repository root.\n - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the README content.\n
- Capability inventory: The skill utilizes
Read,Grep, andBashto interact with and process file content as described inSKILL.md.\n - Sanitization: Absent; the skill does not include steps to sanitize, escape, or validate the content of the markdown files before derivation or translation.
Audit Metadata