glean-webhooks-events

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to receive and process untrusted external data from source system webhooks (e.g., GitHub, Confluence, Notion).
  • Ingestion points: The TypeScript Express handler in SKILL.md accepts POST requests with JSON payloads.
  • Boundary markers: The code implements a verifyGleanSignature middleware that validates the x-glean-signature header using HMAC-SHA256 and a secret key.
  • Capability inventory: The skill environment is configured with Bash(npm:*), Read, Write, and Edit tools to manage indexing tasks.
  • Sanitization: The instructions explicitly mandate source authentication, timestamp validation, and the rejection of malformed payloads or unknown origins to mitigate risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — glean-webhooks-events