living-reviews-in-relativity

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 read local resource files and search external websites, which introduces a surface where untrusted data could potentially influence agent behavior.\n
  • Ingestion points: The skill explicitly directs the agent to read ../../resources/source-basis.md and ../../resources/official-source-map.md, and to perform web searches for current Springer author guidelines.\n
  • Boundary markers: Absent. There are no instructions provided to the agent to treat this ingested content as untrusted or to ignore any embedded directives within those sources.\n
  • Capability inventory: The skill relies on the agent's standard file-reading and web-searching capabilities. It does not utilize high-risk tools such as shell execution or arbitrary network writing.\n
  • Sanitization: Absent. The skill provides no mechanisms or instructions for validating or filtering the content retrieved from the specified external and local sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — living-reviews-in-relativity