groove-work-compound
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the entire conversation history and deferred items provided by the user to update project rules, templates, and documentation. This creates a standard ingestion surface for instructions embedded in processed data.
- Ingestion points: Full chat thread context and the
.groove/.cache/pending-capture.mdfile (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the ingested session data.
- Capability inventory: The skill has the ability to read/write/edit files, execute
gitcommands via a restrictedBashtool, and trigger internal memory and task management utilities (SKILL.md). - Sanitization: No explicit sanitization or escaping logic is defined for the content extracted from the conversation before it is written to project files.
Audit Metadata