research-brief

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its data ingestion process.
  • Ingestion points: The agent is instructed to read content from web searches, project context files, user-uploaded documents, and recent emails in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to treat external data as untrusted or to ignore embedded instructions within that data.
  • Capability inventory: The skill utilizes file system access to read existing research and preferences, and it writes the final brief to the /output/ directory.
  • Sanitization: There is no evidence of input validation or sanitization for the content retrieved from external sources before it is synthesized into the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 07:10 AM
Security Audit — agent-trust-hub — research-brief