novelty-check

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of retrieving and analyzing external research content.
  • Ingestion points: Untrusted research literature, abstracts, and metadata are retrieved from external websites using the WebSearch and WebFetch tools (SKILL.md).
  • Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore embedded instructions' warnings to prevent the agent from obeying commands hidden within the fetched documents.
  • Capability inventory: Ingested content is passed directly to the mcp__codex__codex tool for analysis, which creates a vector for external content to influence the model's logic (SKILL.md).
  • Sanitization: Absent; the skill provides no instructions for validation, filtering, or escaping of the external content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 03:14 AM