physical-review-x
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely informational content and logic for venue-selection and manuscript framing. No malicious code or suspicious execution patterns were detected.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The instructions reference relative paths
../../resources/source-basis.mdand../../resources/official-source-map.md. These appear to be internal resource files used for mapping journal metadata and do not involve access to sensitive user credentials or system configurations. - [INDIRECT_PROMPT_INJECTION]: The skill processes manuscript data provided by users to evaluate journal fit.
- Ingestion points: The manuscript content/metadata provided during the interaction.
- Boundary markers: Not explicitly defined in the prompt instructions.
- Capability inventory: The skill is limited to providing textual advice; it does not utilize file-write, network, or subprocess capabilities.
- Sanitization: No specific sanitization or escaping is mentioned, but the risk is minimized by the lack of downstream executable capabilities.
Audit Metadata