NYC

parallel-literature-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external sources and processes it through a synthesis agent.
  • Ingestion points: Search results from PubMed (abstracts) and the web (via Perplexity) are retrieved and fed into the synthesis agent's context.
  • Boundary markers: The skill documentation does not specify the use of clear delimiters or 'ignore' instructions to prevent the model from following commands hidden within retrieved search results.
  • Capability inventory: The skill is primarily focused on text synthesis and report generation; it does not appear to expose high-risk tools such as shell access or file-system modifications to the untrusted input.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved external content before it is interpolated into the synthesis prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM