polpo-runtime
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of architectural documentation, integration references, and metadata. It contains no executable scripts or commands that pose a risk to the host environment.
- [SAFE]: The provided documentation explicitly outlines robust security measures, including secret redaction, private-network blocking, and the use of 'guardrail packs' (standard, strict, and custom) to sanitize input and output.
- [SAFE]: Guidelines for 'Project Loops' and 'Durable Runs' prioritize data integrity by enforcing schema validation, idempotency keys, and protected context roots (e.g.,
request.metadata). - [SAFE]: The skill includes best-practice advice for handling untrusted data, such as bounding and escaping nested delimiters to prevent prompt injection and context confusion.
Audit Metadata