sync-spec
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/check_trace.pyandscripts/check_graph.py) to verify documentation traceability and update project visualizations. These scripts are invoked via thepython3command and operate on local project files. - [PROMPT_INJECTION]: The skill processes markdown documentation which acts as an untrusted input surface, creating a potential for indirect prompt injection.
- Ingestion points: Documentation files located in
docs/specs/and configuration settings indocs/agents/project.md. - Boundary markers: No explicit delimiters or guardrail instructions are used to isolate documentation content from the agent's core logic.
- Capability inventory: The agent has the ability to execute shell commands (
python3) and modify files throughout the repository. - Sanitization: No automated sanitization is present; however, the skill incorporates human-in-the-loop checkpoints, such as requiring explicit user approval for spec status transitions and manually resolving 'orphan' items.
Audit Metadata