pnpm-action-setup-cache

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface detected because the skill requires processing untrusted external workflow YAML files.
  • [PROMPT_INJECTION]: Ingestion points: .github/workflows/*.yml files.
  • [PROMPT_INJECTION]: Boundary markers: Absent; no delimiters or ignore-instructions are specified for the workflow content.
  • [PROMPT_INJECTION]: Capability inventory: Agent has capability to read and modify (write) workflow configuration files.
  • [PROMPT_INJECTION]: Sanitization: Absent; no validation or escaping of the ingested file content is required.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:31 AM