sr-screener
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted research data (RIS exports, PDFs), creating a potential surface for indirect prompt injection.\n
- Ingestion points: Bibliographic exports are parsed in
scripts/prepare_records.py, and full-text PDFs are read inscripts/prepare_fulltext.py.\n - Boundary markers: The skill defines an instruction-data boundary in
SKILL.mdandagents/screening_reviewer_agent.mdto prevent data from being interpreted as instructions.\n - Capability inventory: Reviewer subagents are restricted to
ReadandGreptools, limiting exposure.\n - Sanitization:
srlib.pysanitizes CSV/XLSX exports by escaping formula-triggering characters.\n- [DYNAMIC_EXECUTION]:scripts/build_workflow.pygenerates JavaScript scripts for theWorkflowtool using predefined templates filled with configuration data.\n- [PROMPT_INJECTION]:SKILL.mdincludes a[direct-mode]token that bypasses intent clarification, overriding routing logic while remaining within safe operational boundaries.
Audit Metadata