ripgrep

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests user-provided search patterns and goals to construct shell commands for execution.
  • Ingestion points: Untrusted data enters the agent context via the [search-goal-or-pattern] argument defined in SKILL.md.
  • Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers when interpolating user input into the final rg command.
  • Capability inventory: The skill is configured to operate with access to Bash, Read, Glob, Grep, and Write tools, which could be leveraged if an injection occurred.
  • Sanitization: The skill includes helpful mitigations by documenting shell-safe quoting practices for Windows and POSIX environments and recommending literal searches (-F) to minimize interpretation of hostile patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:49 PM
Security Audit — agent-trust-hub — ripgrep