meeting-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of meeting transcripts from various file formats (.txt, .md, .vtt, .srt, .docx, .json).
- Ingestion points: Reads all transcript files found in a target directory and normalizes their content for analysis (SKILL.md, Core Workflow sections 1 & 2).
- Boundary markers: The instructions do not define explicit delimiters or 'ignore instructions' markers to wrap the ingested transcript content before it is processed by the LLM.
- Capability inventory: The skill performs directory scanning, file reading, and complex natural language processing/summarization. It does not explicitly define network operations or shell execution capabilities in its internal logic.
- Sanitization: There is no mention of sanitizing or filtering the transcript content for malicious instructions or hidden control tokens before the analysis modules are executed.
Audit Metadata