better-auth-profile
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to fetch a Markdown file from an external domain using
curl https://fullstackrecipes.com/recipes/better-auth-profile.md. This introduces content from a third-party source not within the trusted vendor lists. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source, creating a surface for indirect prompt injection.
- Ingestion points: External content is ingested via the
curlcommand inSKILL.mdtargetingfullstackrecipes.com. - Boundary markers: There are no delimiters or warnings to ignore embedded instructions within the fetched Markdown file.
- Capability inventory: The skill itself does not specify high-privilege capabilities, but the agent processing the instructions may have access to the local filesystem or other tools.
- Sanitization: The skill does not provide any mechanism to sanitize or validate the external content before it is processed by the agent.
Audit Metadata