terraform-consumer-implement

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data from GitHub issues that could contain malicious instructions designed to manipulate the agent's behavior.
  • Ingestion points: Reads data from 'gh-issue.json' and uses the 'gh issue view' command to retrieve issue details.
  • Boundary markers: None. The instructions do not specify any delimiters or safety prompts to isolate external content from the GitHub issue.
  • Capability inventory: Includes executing 'terraform' commands (init, plan, apply), 'gh' CLI commands for issue/PR management, and execution of local bash scripts.
  • Sanitization: No sanitization or validation of external input is mentioned or implemented.
  • [COMMAND_EXECUTION]: The skill executes system-level commands including 'terraform' and the GitHub 'gh' CLI. It also runs a local bash script located at '/workspace/.specify/scripts/bash/validate-env.sh'. While these are core to the skill's functionality, they provide a significant attack surface if the agent's logic is subverted by malicious input from the processed GitHub issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:17 AM