summarize
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external sources including URLs and YouTube transcripts, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Content is ingested from external URLs and YouTube video transcripts via the summarize command-line tool.
- Boundary markers: Absent. The skill instructions do not define any delimiters or system instructions to isolate untrusted content from the agent's core instructions.
- Capability inventory: The skill utilizes the summarize binary to process content and interface with multiple LLM providers (OpenAI, Anthropic, Google, xAI).
- Sanitization: Absent. There is no evidence of input validation or sanitization mechanisms to prevent malicious instructions embedded in the external content from influencing the agent's behavior.
Audit Metadata