skills/vale-cli/agent-tools/triage/Gen Agent Trust Hub

triage

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line tools, specifically vale and jq, to analyze project files and generate reports. These operations are performed locally and align with the skill's primary purpose of linting triage.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data generated by the vale tool.
  • Ingestion points: Data is read from a temporary file /tmp/vale.json created by the vale command.
  • Boundary markers: None explicitly defined in the instructions, as the data is processed via structured jq filtering.
  • Capability inventory: Execution is limited to local shell commands for data processing and reporting.
  • Sanitization: The skill uses jq to parse structured JSON, which inherently treats keys and values as data rather than instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 08:41 AM
Security Audit — agent-trust-hub — triage