ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external untrusted text.
- Ingestion points: The agent reads user-provided files in 'Step 1: Read the Content'.
- Boundary markers: There are no instructions for using delimiters to isolate source content.
- Capability inventory: The skill uses the 'Read' and 'Write' tools to process inputs and save the final Markdown plan.
- Sanitization: The agent is not directed to validate the content or ignore instructions found within the source files.
Audit Metadata