help
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
git statusand file globbing to retrieve project metadata. These operations are intended for gathering ambient context to provide better command routing and are restricted to status and file listing. - [PROMPT_INJECTION]: The skill displays a vulnerability surface for indirect prompt injection as it processes data from untrusted files in the repository to make routing decisions.
- Ingestion points: Files located in
.claude/plans/and.claude/solutions/are read and used as signals for intent classification. - Boundary markers: No delimiters or instructions are used to separate the ingested file content from the skill's own logic.
- Capability inventory: The skill has the ability to recommend a wide range of commands, including those that execute code or perform audits, based on the content of the ingested files.
- Sanitization: The skill does not perform any sanitization or validation of the content extracted from the plan or solution files.
Audit Metadata