callbacks-and-input

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents the registration of callbacks designed to process untrusted data from external clients.
  • Ingestion points: The on_message, on_input, and on_unicode callbacks in SKILL.md ingest data (text, binary, and input events) directly from connected clients.
  • Boundary markers: The provided Python and C code snippets do not demonstrate the use of delimiters or 'ignore' instructions for the data being processed.
  • Capability inventory: The skill documents capabilities to print data, handle input events, and send messages back to the client (send_message). It does not demonstrate high-risk capabilities like arbitrary command execution or file system writes.
  • Sanitization: The snippets do not include explicit sanitization or validation logic for the inbound message strings or input payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:49 PM
Security Audit — agent-trust-hub — callbacks-and-input