one-list-work

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of tools (list-planned-work, list-completed-work, list-blockers, list-initiatives, list-bugs) designed to interact with the One Horizon MCP.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (One Horizon). While this creates a surface for indirect prompt injection if task titles or descriptions contain malicious instructions, the skill does not possess high-risk capabilities like arbitrary command execution or network exfiltration that would allow for successful exploitation.
  • Ingestion points: Data fetched via One Horizon MCP tools in SKILL.md.
  • Boundary markers: Not present.
  • Capability inventory: No dangerous capabilities (subprocesses, file writes, or direct network calls) are present in the skill files.
  • Sanitization: No specific sanitization or filtering logic is defined for the fetched data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:47 AM
Security Audit — agent-trust-hub — one-list-work