ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (YouTube transcripts, articles, tutorials) to generate actionable plans, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill uses the
Readtool to analyze user-provided files at a specifiedFILE_PATHas described in Step 1 ofSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or directives to the agent to ignore prompt-like instructions that might be embedded within the source content during extraction.
- Capability inventory: The skill utilizes both
ReadandWritecapabilities to analyze external content and subsequently save generated plans to the local filesystem. - Sanitization: There is no evidence of sanitization or validation of the ingested content to prevent instructions in the data from overriding the agent's behavior during the plan creation phase.
Audit Metadata