astrofy-page-planner
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external local project files and user-provided samples, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: The skill reads local files including
.astrofy/docs/index.md, project configurations, routes, and design system files, and it accepts user-provided article samples as tone and voice references.\n - Boundary markers: The instructions do not require the use of explicit delimiters or protective prompts to isolate the ingested external content from the agent's primary instructions.\n
- Capability inventory: The skill has the capability to write files to the project directory (
.astrofy/pages/), execute a local CLI tool (astrofy), and delegate tasks to downstream implementation skills.\n - Sanitization: No mention is made of sanitizing, validating, or filtering the content retrieved from local files or user-supplied editorial samples before it is processed by the agent.
Audit Metadata