setup-llms-txt
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to perform a network request to
https://www.inlay.dev/api/auditusingcurl. While this is intended for auditing the site's AI readiness, it involves sending the user's site URL to an external third-party service. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem and remote web content to generate documentation files.
- Ingestion points: The skill reads local project files including
package.json, configuration files, and up to 20 Markdown/MDX files to understand project structure. It also fetches the existingllms.txtfrom a remote URL. - Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the files being analyzed.
- Capability inventory: The skill possesses the capability to write files to the local disk (
llms.txt,llms-full.txt) and perform network operations viacurl. - Sanitization: No sanitization or validation steps are defined for the content extracted from project files before it is used to generate the new documentation files.
Audit Metadata