scout-profile

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data when users provide existing CV files or text for parsing, which creates a surface for indirect prompt injection. 1. Ingestion points: User-provided CV files or pasted text in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Reading and writing files in ~/.scout/profile/ as defined in SKILL.md. 4. Sanitization: Absent.
  • [DATA_EXFILTRATION]: No network operations or data transmission patterns were detected. All profile data is managed within the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:48 PM