flag-revisions

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and displays data from the GrowthBook API that may contain user-controllable content (such as draft comments, rule names, and flag metadata).
  • Ingestion points: Data retrieved through gb-call from endpoints like /api/v2/features/:id/revisions and /api/v2/flag-revisions (as documented in SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard instructions that might be embedded in the fetched GrowthBook data.
  • Capability inventory: The skill uses the gb-call tool (via Bash) which has capabilities to both read from and write to (PUT, POST) the GrowthBook API.
  • Sanitization: There is no mention of sanitizing or escaping the data returned by the API before it is processed or presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:28 PM
Security Audit — agent-trust-hub — flag-revisions