refine-task

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted task data (titles, descriptions, and comments) using the get_task and list_tasks tools. Malicious instructions hidden within these task fields could attempt to override the agent's behavior during the refinement process.\n
  • Ingestion points: Task content retrieved via get_task and list_tasks in SKILL.md.\n
  • Boundary markers: Absent. The instructions do not provide explicit delimiters or clear directives to the agent to treat the retrieved task content as data only and to ignore any embedded commands.\n
  • Capability inventory: update_task, create_task_comment, update_artifact, and codebase exploration (searching for related files/patterns) as defined in SKILL.md.\n
  • Sanitization: No input validation or content filtering is performed on the ingested task data before it is incorporated into the agent's reasoning workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:43 AM
Security Audit — agent-trust-hub — refine-task