skills/howells/arc/suggest/Gen Agent Trust Hub

suggest

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior or high-risk patterns were identified. The skill's operations, including codebase analysis and task tracker integration, are consistent with its stated purpose.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external content from the codebase and task managers.
  • Ingestion points: .arc/log.md, Linear issues, TaskList, codebase content (TODOs/FIXMEs), and docs/vision.md.
  • Boundary markers: None identified in the workflow to separate ingested data from instructions.
  • Capability inventory: Spawns sub-agents for exploration and research, interacts with MCP tools for Linear integration, and recommends CLI commands for user execution.
  • Sanitization: No explicit sanitization or validation of codebase or task content is documented in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 09:28 AM