skills/talkstream/ru-text/ru-check/Gen Agent Trust Hub

ru-check

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it processes untrusted text from user arguments or previous conversation history.
  • Ingestion points: Untrusted data enters the context via the $ARGUMENTS variable or by reviewing the most recent text output.
  • Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the text being analyzed.
  • Capability inventory: The skill is restricted to read-only file operations (Read, Grep, Glob) and explicitly disallows all write and shell execution tools (Write, Edit, Bash, PowerShell, Monitor).
  • Sanitization: No explicit sanitization or validation of the input text is performed.
  • Note: The risk is effectively mitigated by the skill's restrictive toolset and the platform-level 'disable-model-invocation: true' setting, preventing the agent from executing commands or modifying the system based on malicious input.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 05:08 PM
Security Audit — agent-trust-hub — ru-check