do-task

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface exists because the skill follows instructions within local project files like ROADMAP.md. This is the skill's primary purpose and is considered safe.
  • Ingestion points: docs/ROADMAP.md, docs/SPEC.md, docs/STYLES.md.
  • Boundary markers: None.
  • Capability inventory: Glob, Read, WebSearch, AskUserQuestion, and file modification.
  • Sanitization: None.
  • [DATA_EXFILTRATION]: The skill accesses local project metadata and uses the WebSearch tool for research. No malicious exfiltration patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:13 AM