ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data provided by the user, such as YouTube transcripts and articles.
- Ingestion points: Data enters the agent context through the Read tool when processing user-supplied file paths as described in the SKILL.md implementation steps.
- Boundary markers: The skill does not explicitly define delimiters or specific instructions to disregard potentially malicious commands embedded within the learning material during the extraction phase.
- Capability inventory: The skill uses the Read and Write tools to analyze text and generate local Markdown files.
- Sanitization: There is no evidence of content sanitization or validation logic to filter potentially harmful input within the instruction set.
Audit Metadata