circulation

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions create a vulnerability surface by directing the agent to process data from external, potentially untrusted sources.
  • Ingestion points: The 'Official-submission checklist' section in SKILL.md instructs the agent to read external files (../../resources/source-basis.md, ../../resources/official-source-map.md) and to search the live web for 'Circulation author instructions'.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore malicious content embedded within these external sources.
  • Capability inventory: The agent is expected to perform file reading and web search operations to fulfill the skill's requirements.
  • Sanitization: There are no explicit instructions for the agent to sanitize, validate, or filter content retrieved from the web or external resource files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — circulation