webhook-subscriptions

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of mapping external webhook data to agent prompts.
  • Ingestion points: Incoming HTTP POST payloads from external services (e.g., GitHub, Stripe, GitLab) are ingested as documented in SKILL.md under the 'Common Patterns' section.
  • Boundary markers: Absent. The documentation shows simple {field} interpolation templates without any delimiters or system instructions designed to prevent the agent from obeying instructions embedded within the variables.
  • Capability inventory: The skill triggers agent runs based on these webhooks and supports delivery of the resulting output to external adapters including Telegram, Discord, and GitHub comments.
  • Sanitization: The skill description and instructions do not mention any sanitization, escaping, or validation of the incoming payload fields before they are interpolated into the prompt string.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:07 AM