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, andfind-documentsas 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, andreport-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