GSD Codebase Mapper
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses PowerShell cmdlets like
Get-ChildItem,Select-String, andGet-Contentto perform local filesystem discovery and file reading. These operations are aligned with the skill's primary purpose of mapping and documenting codebases. - [PROMPT_INJECTION]: Vulnerable to indirect prompt injection because the agent ingests untrusted data from the codebase it is analyzing.
- Ingestion points: Reads various project files (
package.json,requirements.txt, source code) usingGet-ContentandSelect-Stringcommands. - Boundary markers: The instructions lack explicit delimitation or warnings to ignore malicious instructions embedded in the analyzed code or comments.
- Capability inventory: The skill is restricted to local filesystem read operations and directory traversal; it lacks network access or file-write capabilities in its defined commands.
- Sanitization: No sanitization or validation of the ingested code content is implemented before the agent interprets it for documentation purposes.
Audit Metadata