promovaweb-devops-review-n8n-stack

Warn

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: MEDIUMPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructs the agent to read sensitive configuration files, specifically postgres.yaml, to inspect database passwords. Accessing credential-bearing files is a high-risk operation, though it is the intended primary purpose of this auditing skill. No external network transmission was detected.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from an external configuration file without adequate security boundaries.
  • Ingestion points: The skill reads the entire content of n8n.yaml and postgres.yaml into the agent's context.
  • Boundary markers: Absent. The instructions do not define delimiters or provide 'ignore embedded instructions' warnings for the data being read.
  • Capability inventory: The agent has the capability to read local files and write the resulting audit report to a new file (n8n.audit.md).
  • Sanitization: Absent. There is no mention of validating or sanitizing the YAML content before the agent evaluates it against the audit checklist.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 04:36 PM