astrofy-homepage
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to generate or modify web components, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads 'authorized content', 'audience' data, and 'main action' objectives from the prompt or project configuration (SKILL.md).
- Boundary markers: Absent; the skill does not define delimiters to separate instructions from the data being processed, nor does it warn the agent to ignore embedded instructions.
- Capability inventory: The skill has the capability to modify project files (Astro routes and components) and execute shell commands via
astrofy checkandastrofy-editorial-review(SKILL.md). - Sanitization: Absent; there are no instructions to sanitize, escape, or validate the input content before it is interpolated into the generated code.
Audit Metadata