linktree-security-basics
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions explicitly prohibit the agent from requesting or handling passwords, recovery codes, browser cookies, or session material, mitigating risks of credential theft.
- [SAFE]: The skill uses the
WebFetchtool to access official documentation from Linktree's help center and primary domain (linktr.ee), which are well-known services. These network operations are limited to informational resources. - [SAFE]: The instructions implement data protection boundaries by requiring the use of sanitized fixtures, redacted control matrices, and owner-approved processes for any changes.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface as it reads external documentation and local repository files. However, the risk is mitigated by explicit instructions to use sanitized data and restricted tool sets. This vulnerability surface is inherent to the skill's function and handled with appropriate safeguards.
Audit Metadata