research

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted external data from sources like documentation and source code.
  • Ingestion points: Retrieves content from external URLs (official docs, specs, APIs) and local source code as specified in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific markers to distinguish between data and agent instructions during the research process.
  • Capability inventory: The skill has the capability to write research findings back into the repository as Markdown files.
  • Sanitization: No explicit sanitization, validation, or filtering of the external content is mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 09:18 AM
Security Audit — agent-trust-hub — research