talk-stage1-extract
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source material (articles, transcripts, notes), creating a surface for indirect prompt injection.
- Ingestion points: Source material is ingested via file paths or inline content provided as input.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill uses 'Read' and 'Write' tools to interact with local files.
- Sanitization: No validation or escaping of the input content is performed before processing or outputting to disk.
Audit Metadata