lumos-audit-props
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The script extracts JSDoc comments from component files and prints them to the console. This creates a surface where malicious instructions embedded in the audited code's comments could be displayed to the agent.\n
- Ingestion points: The script
audit-props.mjsreads.astrofiles from the specified source directory (defaulting tosrc/components).\n - Boundary markers: The script uses regular expressions to extract documentation blocks but does not employ specific delimiters or warnings to prevent the agent from interpreting the extracted text as instructions.\n
- Capability inventory: The skill is limited to local file reading and console output; it does not have capabilities for network access, file writing, or command execution.\n
- Sanitization: Extracted documentation strings are printed directly to the console without filtering or sanitization.
Audit Metadata