literature-search

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local bash scripts (scripts/search) and Node.js files (scripts/search.mjs) for searching and setup. It also utilizes system utilities such as find to resolve script paths and jq to parse JSON results.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from external sources.
  • Ingestion points: Full-text scientific content retrieved from PubMed, arXiv, bioRxiv, and medRxiv via the api.valyu.ai endpoint.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are used when processing the retrieved article content.
  • Capability inventory: The agent has the capability to execute shell commands and local scripts (scripts/search) as part of the skill's workflow.
  • Sanitization: There is no documented evidence of sanitization, filtering, or validation performed on the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:32 AM