find-your-level
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a roadmap configuration file (
ROADMAP.md) from the author's official GitHub repository to determine time estimates for learning phases. This is a legitimate functional dependency on a vendor-owned resource. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse content from a remote source (
ROADMAP.md) into the agent's context. This constitutes a standard injection surface where a compromised remote file could theoretically introduce malicious instructions, although the risk is minimized by the use of a trusted author repository. - Ingestion points: Remote
ROADMAP.mdreferenced inSKILL.md. - Boundary markers: None specified for the fetched content.
- Capability inventory: The skill directs the agent to create and update a persistent
LEARNING.mdfile based on the quiz results. - Sanitization: No explicit instructions for sanitizing or escaping the fetched remote content were found.
Audit Metadata