NYC

ship-learn-next

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill is designed to ingest and process untrusted data from external files (like transcripts or articles) and incorporate that data into its reasoning process.
  • Ingestion points: The skill uses the Read tool in 'Step 1' to ingest user-provided content from variable file paths.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings when instructing the agent to analyze the content.
  • Capability inventory: The skill possesses Read and Write tool capabilities. While it cannot execute arbitrary shell commands, it can be manipulated into writing misleading or malicious content to the file system.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM