learn-anything-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and contains no scripts, binaries, or automated commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided information about their learning goals and background. While it lacks explicit boundary markers or sanitization for this data, the skill has no exploitable capabilities (such as file writing, network access, or command execution), rendering the attack surface non-threatening. (1) Ingestion points: User-supplied goals, experience level, and learning preferences defined in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: None. The skill does not use any tools or scripts. (4) Sanitization: Absent.
Audit Metadata