highlight-scanner

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through processed video transcripts.
  • Ingestion points: The script scripts/find_highlights.py reads external transcript data (SRT/VTT formats) and incorporates the text content into prompts sent to external LLMs (OpenAI/Gemini).
  • Boundary markers: The prompt template in the find_highlights_with_ai function lacks clear delimiters or 'ignore embedded instructions' warnings when interpolating the transcript_lines variable.
  • Capability inventory: The skill has the capability to perform network operations (calling external AI APIs) and provides the results back to the agent environment.
  • Sanitization: There is no evidence of sanitization, filtering, or escaping of the transcript content before it is embedded into the prompt, allowing potential instructions inside a transcript to influence the behavior of the external model.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 07:49 AM