ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and analyze untrusted external content provided by the user, such as YouTube transcripts, notes, and articles. This creates a surface for indirect prompt injection attacks where malicious instructions hidden in the input content could influence the agent's behavior.
- Ingestion points: The
Readtool is used inSKILL.md(Step 1) to ingest file content provided by the user. - Boundary markers: The instructions do not define clear delimiters or specific guidance for the agent to treat the ingested content as data only and to ignore any embedded instructions.
- Capability inventory: The skill utilizes the
ReadandWritetools, allowing it to interpret external data and subsequently create or modify files on the local filesystem. - Sanitization: There is no specified mechanism for sanitizing or filtering the content read from external files before it is used to generate the output plan.
Audit Metadata