astrofy-themes
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process local project files and configuration, which presents an attack surface where malicious content in those files could influence agent behavior.\n
- Ingestion points: Directions include reading the initial theme script, selectors, .astrofy/config/paths.json, lockfiles, and node_modules contents.\n
- Boundary markers: No instructions are given to wrap ingested content in delimiters or to ignore potential instructions embedded within them.\n
- Capability inventory: The skill involves writing project code and executing the
astrofyCLI tool.\n - Sanitization: No sanitization or validation of the ingested data is mentioned.\n
- Remediation: Implement strict delimiters and sanitize data from project files before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill mandates the execution of
astrofy check --category themefor validating the implementation. This is a local command-line utility for project verification.
Audit Metadata