skills/zenon-red/skills/zr-validate/Gen Agent Trust Hub

zr-validate

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, specifically GitHub pull request comments and reviews via the gh pr view command.
  • Ingestion points: The agent reads the content of reviews and comments from a GitHub PR (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the PR content.
  • Capability inventory: The skill has the capability to modify state or record decisions through the probe review validate and probe action complete-merge commands.
  • Sanitization: No sanitization or filtering of the ingested GitHub content is described.
  • [COMMAND_EXECUTION]: The skill uses the probe CLI tool to fetch task information and record validation results, and the gh CLI to interact with GitHub repositories. These operations are consistent with the skill's stated purpose of managing and validating development workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 08:45 PM