workflow-automator

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: A detailed review of the skill's instructions revealed no malicious patterns, unauthorized command execution, or data exfiltration attempts.
  • [NO_CODE]: The skill consists entirely of instructional documentation and does not distribute any scripts, binaries, or external software dependencies.
  • [PROMPT_INJECTION]: The skill instructions involve reading external project configuration files, which is a known surface for indirect prompt injection.
  • Ingestion points: The agent is directed to read package.json, .github/workflows/, and Makefile (SKILL.md).
  • Boundary markers: No specific delimiters or safety warnings for the agent to ignore embedded instructions in these files are provided.
  • Capability inventory: The skill itself does not include or define any custom scripts or tools.
  • Sanitization: There are no instructions for validating or sanitizing the content of the ingested project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:48 PM
Security Audit — agent-trust-hub — workflow-automator