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-callfrom endpoints like/api/v2/features/:id/revisionsand/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-calltool (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