feedback-recall
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process customer feedback data from local files (e.g.,
context/feedback/index.md). - Ingestion points: Reads files from
context/feedback/, including customer quotes and sentiment data. - Boundary markers: The skill lacks explicit instructions to ignore or escape instructions that might be embedded within the customer feedback text itself.
- Capability inventory: The skill performs file read operations and synthesizes summaries, but does not execute subprocesses, network requests, or file-write operations based on the input.
- Sanitization: No explicit sanitization or escaping of the ingested feedback content is defined before it is interpolated into the final markdown report.
Audit Metadata