Knack Expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted data from an external Knack database and possesses editing capabilities, creating a potential surface for indirect prompt injection.
  • Ingestion points: Fetches database records via the GET /v1/objects/{object_key}/records endpoint as described in SKILL.md.
  • Boundary markers: None specified; the skill does not explicitly instruct the agent to ignore instructions embedded within the fetched data.
  • Capability inventory: Includes 'Read' and 'Edit' tools, plus the ability to trigger Vercel deployments and perform data exports.
  • Sanitization: No mention of input validation or sanitization for data retrieved from the database before it is processed by the agent.
  • [Data Exposure & Exfiltration] (SAFE): The skill documentation refers to Knack API authentication headers (X-Knack-REST-API-Key) but does not contain any hardcoded secrets, private keys, or unauthorized data access patterns.
  • [Remote Code Execution] (SAFE): No patterns for downloading or executing remote scripts or unverified third-party packages were identified.
  • [Prompt Injection] (SAFE): There are no instructions attempting to override system behavior, bypass safety filters, or reveal system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:42 PM