meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting and analyzing external data. Ingestion points: The 'Discover Available Data' section instructs the agent to scan local folders for various transcript file formats (.txt, .md, .vtt, .srt, .docx). Boundary markers: The instructions do not define delimiters or specify that content within transcripts should be treated purely as data rather than instructions. Capability inventory: The skill is limited to text analysis and summary generation; it does not request or demonstrate use of high-risk capabilities like network access, file system modification, or subprocess execution. Sanitization: No measures for validation, filtering, or escaping transcript content are provided in the instructions.
Audit Metadata