Skills
skills/rwx-cloud/skills/review-gha-migration/Gen Agent Trust Hub

review-gha-migration

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it reads and analyzes external configuration files (GitHub Actions workflows and RWX configs). A malicious file could contain instructions designed to manipulate the agent's review logic or influence its output summary. \n
  • Ingestion points: .rwx/ci.yml and .github/workflows/ files specified in the review procedure (SKILL.md)\n
  • Boundary markers: Absent; instructions do not provide delimiters or "ignore instructions" tags for the ingested content\n
  • Capability inventory: Shell access used for executing the rwx CLI tool (SKILL.md)\n
  • Sanitization: Absent; the skill does not specify validation or sanitization of the YAML content before processing.\n- [COMMAND_EXECUTION]: The skill uses the rwx CLI tool to perform actions such as rwx docs pull, rwx docs search, and rwx lint. These operations are consistent with the skill's primary purpose and involve resources provided by the skill's author (rwx-cloud).
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 08:28 PM