cs-explore
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python utility script (
.codestable/tools/search-yaml.py) to search and filter metadata within its local documentation directory. This is a controlled execution of a vendor-provided tool necessary for its documentation management functions. - [PROMPT_INJECTION]: The skill processes untrusted content from the repository's source code, making it theoretically vulnerable to indirect prompt injection.
- Ingestion points: The skill reads repository content using search and read tools to generate summaries and conclusions (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions found within the code files being analyzed.
- Capability inventory: The skill has the ability to write documentation to the local filesystem (
.codestable/compound/) and execute a local helper script. - Sanitization: No sanitization or content validation is performed on the data ingested from the repository before it is used to formulate conclusions.
Audit Metadata