astrofy-security
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze untrusted project data including HTML, scripts, and MDX content, which provides an attack surface for indirect prompt injection.
- Ingestion points: The instructions direct the agent to read external inputs, HTML render points, and MDX files from the analyzed project (SKILL.md, references/technical.md).
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" headers for the agent to use when reading these untrusted files into its context.
- Capability inventory: The skill utilizes file system read access and invokes the
astrofy checkshell command to perform its audits (SKILL.md). - Sanitization: The skill provides high-quality security guidance for the agent, such as recommending the use of AST (Abstract Syntax Tree) parsing instead of importing configuration files to prevent code execution during the analysis phase (references/implementation.md).
Audit Metadata