waba-embedded-signup

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted external data.
  • Ingestion points: The agent collects user-provided business details (legal name, website, privacy policy) in SKILL.md (Step 3) and is designed to process webhook payloads described in references/waba-embedded-signup-spec.md.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or explicit warnings to ignore embedded instructions when interpolating this external data into prompts.
  • Capability inventory: The agent utilizes capabilities to perform sensitive operations, such as completing profiles via POST /v3/profiles/{id}/complete and testing webhooks via POST /v3/webhooks/{id}/test.
  • Sanitization: No validation, escaping, or filtering steps are defined for the ingested content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 11:39 AM
Security Audit — agent-trust-hub — waba-embedded-signup