meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface detected. Ingestion points: The skill instructs the agent to scan local folders for transcript files in .txt, .md, .vtt, .srt, and .docx formats (SKILL.md). Boundary markers: No specific delimiters or instructions to ignore embedded commands within the transcripts are provided. Capability inventory: The skill defines no dangerous capabilities such as subprocess execution, file writing, or network requests. Sanitization: No content validation or sanitization of the transcript data is specified. The overall risk is low because the agent has no means to execute high-impact actions even if an injection were successful.
- [SAFE]: The skill consists entirely of markdown instructions. No scripts, binaries, obfuscated content, or external network connections were found.
Audit Metadata