task-management

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it retrieves untrusted content from an external environment and has permission to perform state-changing operations.
  • Ingestion points: Untrusted data enters the agent context through search-tasks, get-task-details, and find-documents as described in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to treat retrieved task content as data rather than instructions.
  • Capability inventory: The skill is capable of substantial mutations using tools such as patch-document, update-initiative, create-todo, and report-bug (SKILL.md).
  • Sanitization: No sanitization or validation logic is defined to inspect retrieved task metadata or document content before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 12:00 PM
Security Audit — agent-trust-hub — task-management