scholar-evaluation
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework is designed to ingest and analyze untrusted scholarly documents (e.g., research papers, proposals), creating a potential attack surface for indirect prompt injection where malicious instructions could be embedded in the research text.\n
- Ingestion points: The skill primarily processes user-provided scholarly work, as defined in the evaluation workflow in
SKILL.md.\n - Boundary markers: The instructions lack explicit boundary markers or "ignore embedded instructions" warnings for the agent when processing the external documents.\n
- Capability inventory: The skill utilizes a local Python script
scripts/calculate_scores.pywhich has the capability to write files to the local file system via the--outputflag.\n - Sanitization: No evidence of input sanitization or content filtering is performed on the ingested research text before it is processed or used to generate reports.
Audit Metadata