housekeep-backlog
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for backlog management, using standard workspace search tools (
rg) to identify tasks and technical debt. No suspicious network operations, credential access, or obfuscation were found. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from source code comments and documentation files during its discovery phase. While this presents an ingestion surface for indirect prompt injection, the skill's scope is limited to classification and documentation within the local environment.
- Ingestion points: Phase 1 scans code markers (TODO, FIXME, WIP, etc.), disabled tests, and project documentation (e.g.,
docs/,plans/) across the workspace. - Boundary markers: None explicitly defined in the discovery instructions to delimit external content from instructions.
- Capability inventory: File system write access (creating/updating
BACKLOG.md) and generating instructions for hand-off to other development skills. - Sanitization: No specific sanitization or filtering logic is described for the content extracted from the workspace.
Audit Metadata