meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting transcripts, creating a vulnerability to indirect prompt injection where instructions hidden within a transcript could influence the agent's behavior during analysis.
- Ingestion points: The skill instructions direct the agent to scan and read various transcript file formats (
.txt,.md,.vtt,.srt,.docx) from a local directory. - Boundary markers: There are no instructions defining delimiters or explicit "ignore embedded instructions" warnings to isolate the transcript data from the analysis logic.
- Capability inventory: The skill is designed for text analysis and generates markdown summaries; it does not include instructions for network operations, file writing, or command execution.
- Sanitization: The skill lacks logic to sanitize, escape, or validate the content of the transcript files before processing.
Audit Metadata