simplified-project-management

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses a hosted MCP connector at a domain associated with the Simplified platform (apikit.simplified.com), which is consistent with its stated purpose of managing Simplified project-management data.
  • [PROMPT_INJECTION]: The skill retrieves and processes external content from the Simplified platform, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: External data is ingested through tools like pm_getTask, api_listComments, and pm_getTaskActivity (found in SKILL.md and references/workflows.md).
  • Boundary markers: No explicit use of delimiters or boundary markers is mandated when handling retrieved text content.
  • Capability inventory: The skill possesses broad capabilities, including creating, modifying, and deleting tasks, boards, and statuses (pm_createTask, pm_updateTask, pm_deleteTask, pm_deleteBoard).
  • Sanitization: There is no mention of sanitizing or escaping retrieved content before the agent interprets or processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 08:59 AM
Security Audit — agent-trust-hub — simplified-project-management