astrofy-react
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads local project files, creating an attack surface where malicious instructions in those files could influence agent behavior.
- Ingestion points: Reads
package.json,astro.config.*,.astrofy/config/paths.json, and project lockfiles (SKILL.md). - Capability inventory: The skill triggers subprocess execution via the
astrofy checkcommand. - Boundary markers: No specific delimiters or instructions to ignore embedded content within the ingested files are provided.
- Sanitization: There is no mention of sanitizing or validating the content of the project files before processing.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute a domain-specific command,
astrofy check --category react, to verify the implementation (SKILL.md,examples/cases.md). - [EXTERNAL_DOWNLOADS]: The skill references and directs the agent to consult official documentation from the Astro project (
docs.astro.build) for technical specifications and integration rules (references/implementation.md,references/technical.md).
Audit Metadata