housekeep-backlog

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the workspace, including code comments and markdown documentation, which presents an attack surface for indirect prompt injection.
  • Ingestion points: Phase 1 involves scanning the entire workspace using rg (ripgrep) to extract content from code markers (TODO/FIXME/HACK), plan documents, and disabled tests.
  • Capability inventory: The skill has the capability to read any file in the workspace, execute search commands, and write to BACKLOG.md. It also suggests handing off tasks to other skills like complete-everything or burndown-full.
  • Sanitization: The instructions do not specify any sanitization, filtering, or escaping for the content retrieved from the workspace before it is interpreted by the agent.
  • Boundary markers: No delimiters or explicit warnings are used to isolate the ingested text markers from the agent's logic during the classification phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:27 PM