linktree-install-auth

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the Linktree SDK through standard package registries (npm and pip). These downloads target a well-known service and are consistent with the skill's stated purpose.
  • [COMMAND_EXECUTION]: Uses basic shell commands to configure environment variables and install dependencies. The commands are transparent and restricted to specific package manager operations in the frontmatter configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides examples for ingesting data from the Linktree API, which represents a potential surface for indirect prompt injection. This behavior is associated with the primary intended purpose of the skill.
  • Ingestion points: Profile and link data are retrieved from the Linktree API via the SDK in SKILL.md.
  • Boundary markers: No explicit delimiters or warnings to ignore data-embedded instructions are provided in the verification examples.
  • Capability inventory: The skill is configured with access to Bash, Write, and Edit tools.
  • Sanitization: Code examples show direct output of retrieved profile data without explicit sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:51 AM
Security Audit — agent-trust-hub — linktree-install-auth