polpo-sdk

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of the @polpo-ai/sdk package from the official npm registry. This is the intended distribution method for the SDK and matches the skill's purpose.
  • [DATA_EXFILTRATION]: The SDK facilitates network operations to https://api.polpo.sh. This is the documented API endpoint for the service and is used to transmit chat messages and manage AI agents as expected.
  • [PROMPT_INJECTION]: The skill provides an interface for sending user-controlled data to AI agents, which is an inherent feature of AI integration SDKs. This represents a potential surface for indirect prompt injection if untrusted data is processed. 1. Ingestion points: ChatCompletionRequest.messages field in SKILL.md and references/types.md. 2. Boundary markers: The provided examples do not demonstrate the use of delimiters or specific instructions to ignore embedded commands in user messages. 3. Capability inventory: The SDK allows the creation of agents with powerful tool access (e.g., bash, read, grep) and supports task execution via the API. 4. Sanitization: No explicit sanitization or input validation logic is included in the basic integration examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 12:20 PM