search-query-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by design.\n
  • Ingestion points: Processes external, untrusted search term reports retrieved from APIs or provided via files (referenced in 'Tooling \u0026 Automation').\n
  • Boundary markers: Absent. There are no instructions to the agent to treat search query content as untrusted or to ignore embedded instructions within that data.\n
  • Capability inventory: The skill has access to the bash tool, git operations, and file system reads/writes.\n
  • Sanitization: Absent. No mention of sanitizing or validating search query data before processing it through the agent's logic.\n- [COMMAND_EXECUTION]: The skill explicitly grants access to the bash tool for tasks such as executing commands, running tests, and reading logs. While standard for many developer-oriented agents, this capability increases the potential impact if the agent is manipulated via indirect prompt injection from the search data it analyzes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:51 PM
Security Audit — agent-trust-hub — search-query-analyst