my-content-digest

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data (YouTube transcripts, tweets), which creates a surface for indirect prompt injection.
  • Ingestion points: Content is received from the output of the 'fetch' skill or direct user input as described in the workflow.
  • Boundary markers: The instructions do not define clear delimiters (e.g., XML tags or triple quotes) to separate the untrusted content from the agent's logic.
  • Capability inventory: The skill utilizes AskUserQuestion to interact with users but does not demonstrate direct file-system or network access in the provided instructions.
  • Sanitization: There is no mention of sanitizing or validating the ingested content to prevent embedded instructions from overriding the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:24 PM