promovaweb-devops-review-evolution-go-stack

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external configuration data.
  • Ingestion points: Reads the local evolution-go.yaml file to perform audits.
  • Boundary markers: The instructions lack specific delimiters or ignore-commands to separate the audited YAML content from the agent's logic.
  • Capability inventory: The skill involves reading local files (evolution-go.yaml and potentially postgres.yaml) and writing an audit report to the file system.
  • Sanitization: No explicit sanitization or instruction-filtering is defined for the content of the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 04:37 PM