physical-review-b

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided manuscripts and also instructs the agent to ingest content from local resource files, creating a potential surface for indirect instructions to influence agent behavior.
  • Ingestion points: User-provided manuscripts (implied by the skill's purpose) and local files ../../resources/source-basis.md and ../../resources/official-source-map.md (specified in the Official-submission checklist section).
  • Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious content within these sources.
  • Capability inventory: The skill enables the agent to perform web searches for author guidelines and read local filesystem resources.
  • Sanitization: Absent. There are no instructions to sanitize or validate the content of the manuscripts or resource files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — physical-review-b