skills/simota/agent-skills/atlas/Gen Agent Trust Hub

atlas

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the local environment using standard development tools (e.g., cargo, swift, git) to retrieve project metadata and dependency trees. These operations are restricted to analysis and documentation tasks aligned with the agent's role as defined in reference/module-boundary-evaluation.md and reference/circular-dependency-remediation.md.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data, creating a potential surface for indirect prompt injection.
  • Ingestion points: The agent reads dependency manifests (Cargo.toml, Package.swift, gradle files) and source code modules during analyze, deps, and boundary recipes (reference/module-boundary-evaluation.md).
  • Boundary markers: The instructions do not specify the use of delimiters or "ignore" warnings when the agent interpolates this data into its context.
  • Capability inventory: The agent executes system commands for dependency analysis and generates documentation files (ADR, RFC).
  • Sanitization: No explicit sanitization of the ingested content is defined, though the skill mandates that analysis be grounded in objective metrics.- [EXTERNAL_DOWNLOADS]: The skill references official documentation for the Rust and Swift programming languages in reference/module-boundary-evaluation.md. These are verified, trusted sources used solely for technical guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM