gsd-map-codebase
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external codebase files using 'Read', 'Glob', and 'Grep' tools. Malicious instructions embedded within the scanned codebase could attempt to influence the agent's behavior. The skill does not define explicit boundary markers or sanitization procedures for the ingested code content.
- [COMMAND_EXECUTION]: The skill uses the 'Bash' tool and processes user-supplied '$ARGUMENTS'. The instructions direct the agent to parse these arguments to determine workflow execution paths. If the referenced workflows ('map-codebase.md', etc.) or the agent's interpretation of these instructions results in direct shell execution of unsanitized arguments, it presents a risk of argument injection.
Audit Metadata