polpo-channels
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external messaging providers (WhatsApp, Telegram, Slack, Discord). Ingestion points: Webhook payloads received from external providers as described in architecture.md and conversation-and-media.md. Boundary markers: The skill mandates signature and challenge verification via official adapters in architecture.md, which helps verify source integrity but does not define explicit prompt delimiters for the LLM. Capability inventory: The skill uses the polpo CLI for provisioning (provisioning.md), performs network requests to identity resolvers (trusted-identity-and-tools.md), and handles messaging delivery. Sanitization: External data is normalized into a provider-neutral format using official adapters before being processed by the conversation bridge.
Audit Metadata