skills/andiedie/skills/and-pick/Gen Agent Trust Hub

and-pick

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub repositories, which represents an attack surface for indirect prompt injection.
  • Ingestion points: GitHub issue descriptions, PRD packages, and linked evidence or attachments processed via Read Delivery Unit.
  • Boundary markers: Absent; no delimiters or explicit instructions to ignore embedded commands are defined for the ingested data.
  • Capability inventory: Read-only workflow; the skill identifies work units for recommendation but does not have file-write or network-operation capabilities.
  • Sanitization: Absent; no validation or escaping of external content is specified.
  • [NO_CODE]: The skill consists entirely of markdown-based process instructions and configuration metadata without any accompanying executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 02:58 AM
Security Audit — agent-trust-hub — and-pick