meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external transcript files, which represents an attack surface for instructions embedded in data.
- Ingestion points: The skill scans local directories for transcript files in various formats (
.txt,.md,.vtt,.srt,.docx) as described in the 'Discover Available Data' section of the instructions. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between analysis instructions and potentially malicious commands embedded within the transcript text.
- Capability inventory: The skill's primary capabilities are text analysis, pattern recognition, and reporting. It does not appear to utilize network tools or perform file-write operations based on the processed data.
- Sanitization: No content validation or sanitization logic is specified for the ingested transcript data.
Audit Metadata