skills/frankieramirez/mana/scry/Gen Agent Trust Hub

scry

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script (scripts/map.sh) to interact with GitHub via the gh CLI. This script performs routine repository operations such as creating, updating, and viewing issues and labels.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issue titles and bodies. This content is used to inform the agent's decisions and seed subagents. While this represents an attack surface for indirect prompt injection, the skill employs structured templates and standard CLI parameters to manage this data safely within its intended workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:58 PM
Security Audit — agent-trust-hub — scry