run-research-pipeline

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize outputs from external LLMs (Claude, Gemini, GPT) provided by the user in Phase 3.
  • Ingestion points: User input in Phase 1 via $ARGUMENTS and external model responses pasted by the user in Phase 3.
  • Boundary markers: The skill uses XML-style tags (e.g., <model-response>, <research-pipeline-output>) to structure data, but does not include explicit instructions for the agent to ignore potential commands embedded within the untrusted external text.
  • Capability inventory: The skill orchestrates other tools/skills like research-interviewer and create-research-brief to process the data.
  • Sanitization: There is no evidence of input validation or sanitization for the content provided from external models.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 09:08 AM
Security Audit — agent-trust-hub — run-research-pipeline