cs-explore
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python utility script located at
.codestable/tools/search-yaml.pyto perform metadata-based searches across the documentation files. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it is designed to read and interpret arbitrary source code from the repository.
- Ingestion points: The agent reads repository source code files using Glob, Grep, and Read tools during Phase 2.
- Boundary markers: The instructions do not specify any boundary markers or delimiters to wrap the ingested code, nor do they include warnings to ignore instructions embedded within the code being analyzed.
- Capability inventory: The skill can execute local Python scripts, read files (including configuration files like
.codestable/attention.md), and write new documentation to the filesystem. - Sanitization: No sanitization or filtering of the ingested code content is mentioned before processing or inclusion in documentation.
Audit Metadata