gsd-set-profile
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts a profile argument from the user which is used to modify agent behavior through configuration settings.
- Ingestion points: The argument is provided by the user to the set-profile workflow as described in SKILL.md.
- Boundary markers: The skill description specifies that the workflow performs argument validation for the quality, balanced, and budget profiles.
- Capability inventory: The skill is restricted to using the Read, Write, and Bash tools as defined in the frontmatter.
- Sanitization: An explicit validation step is listed in the process to ensure inputs match the expected model profile names before config.json is updated.
- [SAFE]: The skill manages model profiles using local configuration files and predefined workflows.
- The skill references a local file path at @{{PLATFORM_ROOT}}/get-shit-done/workflows/set-profile.md for its execution logic.
- All file operations are limited to reading and writing the tool's own config.json file.
Audit Metadata