plain-language
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The maintenance script
scripts/fetch_guide.pyusessubprocess.runto execute thepandocbinary for document conversion. This is a standard utility function that processes HTML content into Markdown. The call is implemented securely using a list of arguments without invoking a shell. - [EXTERNAL_DOWNLOADS]: The skill contains a script designed to fetch the latest plain language guidelines from
digital.gov, which is a well-known and official U.S. government domain. This is an expected behavior for keeping the reference materials up to date. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and summarize user-provided text, which inherently creates an attack surface for indirect prompt injection. While an attacker could embed instructions in data to be processed, the skill itself does not have access to sensitive files, network exfiltration tools, or other capabilities that would allow for successful exploitation.
Audit Metadata