spectra-quick
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill accepts a target path via $ARGUMENTS and analyzes up to 25 files from the local filesystem. It lacks explicit boundary markers or sanitization techniques to differentiate between data (code) and instructions, making it vulnerable to indirect prompt injection attacks where malicious content within the analyzed files could hijack the agent's logic.
- Ingestion points: Local files provided via $ARGUMENTS in SKILL.md.
- Boundary markers: Not present.
- Capability inventory: File reading capabilities for up to 25 files on the local filesystem.
- Sanitization: None identified for the content of processed files.
Audit Metadata