astrofy-landing-pages
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
astrofy checkCLI command to validate the output and functionality of the generated landing pages. This is a legitimate part of the skill's developer-focused workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which creates a vulnerability surface if the ingested content contains malicious instructions.
- Ingestion points: Reads campaign offers ("oferta fornecida"), route definitions, and endpoint configurations from project files like
.astrofy/config/paths.jsonand external sources. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the provided offer content or endpoint data.
- Capability inventory: The skill is capable of modifying project files (creating/editing Astro components) and executing shell commands via the
astrofyCLI. - Sanitization: There is no mention of sanitizing, escaping, or validating the provided text or endpoint values before they are used in the page generation process.
Audit Metadata