linktree-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content by using the
WebFetchtool to retrieve official Linktree documentation, pricing, and help articles. - Ingestion points: External URLs from
linktr.eeandhelp.linktr.eeare fetched and parsed as part of the verification workflow defined inSKILL.mdandreferences/official-docs.md. - Boundary markers: The skill does not explicitly use delimiters or specialized instructions to ensure the agent ignores any potentially malicious instructions embedded in the fetched documentation.
- Capability inventory: The skill possesses the
WriteandEdittools, which could be used to persist data or modify repository files based on the content of the external pages. - Sanitization: There is no evidence of content sanitization or validation for the documentation retrieved at runtime.
Audit Metadata