classical-and-quantum-gravity

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external search results and internal resource files, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The skill explicitly directs the agent to read ../../resources/source-basis.md and ../../resources/official-source-map.md, and to "Search the live site for 'Classical and Quantum Gravity author guidelines'".
  • Boundary markers: No explicit boundary markers or instructions to disregard embedded commands in the ingested data are provided.
  • Capability inventory: The skill itself focuses on venue selection and formatting advice and does not include commands for network exfiltration or system modification.
  • Sanitization: No sanitization or validation of the content retrieved from the live site or internal files is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — classical-and-quantum-gravity