meeting-action-item-extractor
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The Python script
extract_action_items.pyuses only built-in standard libraries such asargparse,json,re, anddatetime. It contains no external dependencies or network-based data exfiltration patterns. - [PROMPT_INJECTION]: The skill processes untrusted meeting transcripts, which represents a potential surface for indirect prompt injection if the processed content contains malicious instructions for the agent.
- Ingestion points: The
--transcriptfile is read and processed inextract_action_items.py. - Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill has the capability to read from and write to the local file system using the paths provided via command-line arguments.
- Sanitization: The script extracts data using regular expressions but does not validate or sanitize the transcript content against embedded instructions.
Audit Metadata