snap-grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructs the agent to fetch GitHub issues using gh issue view and explore the local codebase to gather context. These are standard operations for an AI agent's development workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it ingests untrusted data from external sources.
  • Ingestion points: External GitHub issues fetched via gh issue view and content from the local codebase (SKILL.md).
  • Boundary markers: Absent; there are no specific instructions to the agent to delimit or ignore instructions embedded within the fetched data.
  • Capability inventory: The skill utilizes gh issue view and filesystem read access. No file-writing, network exfiltration, or arbitrary command execution capabilities are invoked.
  • Sanitization: No explicit sanitization or validation of the fetched content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 11:56 AM