feature-flags-setup
Warn
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
- External Downloads (MEDIUM): The skill instructs the agent to fetch content from
https://fullstackrecipes.com/api/recipes/feature-flags-setupusingcurl. This domain is not a recognized trusted source, and the content being fetched consists of 'recipes' (instructions/code) that the agent is expected to follow. - Indirect Prompt Injection (MEDIUM): The skill has a significant attack surface because it ingests untrusted external data that influences agent behavior.
- Ingestion points: Remote API call to
fullstackrecipes.cominSKILL.md. - Boundary markers: None; the fetched content is likely interpolated directly into the agent's context.
- Capability inventory: While no direct
evalorsubprocesscalls are in the skill itself, the agent's goal is 'implementation', which typically involves file writes and command execution. - Sanitization: None detected.
Audit Metadata