cs-roadmap
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to perform specific tasks as part of the workflow:
- Execution of
.codestable/tools/search-yaml.pyto query project data. - Execution of
.codestable/tools/validate-yaml.pyto ensure the integrity of roadmap YAML files. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It is designed to ingest data from multiple untrusted sources within the project environment, including:
- Reading
.codestable/attention.mdand various files inrequirements/,architecture/, androadmap/directories. - Processing results from local search tools.
- Ingestion points: Documented in the Phase 2 'Reading Materials' section of SKILL.md.
- Boundary markers: None explicitly defined in the instructions for separating file content from system instructions.
- Capability inventory: Subprocess execution of local Python scripts for searching and validation.
- Sanitization: No evidence of input validation or escaping for content read from project files before it is processed by the agent.
Audit Metadata