ship-learn-next
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a structured learning framework that transforms content (like transcripts or articles) into shippable iterations. It uses the Read tool to analyze input and the Write tool to save markdown plans to a file.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external files. However, given the primary purpose of the skill is content processing and it lacks dangerous capabilities like network access or shell command execution, this is considered a standard operational risk rather than a malicious finding. 1. Ingestion points: Reads user-provided content paths (e.g., transcripts, articles) in Step 1. 2. Boundary markers: None explicitly defined to separate user content from system instructions. 3. Capability inventory: Limited to Read and Write tools; instructions focus on content extraction and plan generation. 4. Sanitization: No specific sanitization or filtering of the input content is mentioned.
Audit Metadata