sync-docs

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from local project files by interpolating them directly into LLM prompts using the @file syntax, making it susceptible to indirect prompt injection if project files contain adversarial instructions.
  • Ingestion points: variables.tf, docs/llms.md, kube.tf.example, README.md, locals.tf.
  • Boundary markers: Not present.
  • Capability inventory: Executes subprocesses via gemini, terraform-docs, terraform, grep, and diff.
  • Sanitization: No sanitization or validation of the ingested file content is performed.
  • [COMMAND_EXECUTION]: The skill automates its workflow by executing various CLI tools.
  • Runs the gemini CLI for variable extraction and content generation.
  • Runs terraform-docs to regenerate documentation from Terraform source files.
  • Uses standard Unix utilities like grep and diff for file comparison and validation.
  • Executes terraform fmt to maintain consistent formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 11:51 PM