setup
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external project files such as
package.json,pyproject.toml,Makefile, and existing documentation to automate the scaffolding of a project configuration. Malicious content within these files could potentially influence the setup process or the configuration read by other skills.\n - Ingestion points: Reads project manifests (
package.json,pyproject.toml,Makefile) and documentation files (AGENTS.md,CLAUDE.md,docs/PRD.md) as specified in the logic ofSKILL.md.\n - Boundary markers: The instructions do not define the use of delimiters or 'ignore' instructions when processing the content of these external project files.\n
- Capability inventory: The skill performs file system writes to
docs/dev-agents/config.mdand executes CLI commands throughgitandghtools.\n - Sanitization: No explicit sanitization or validation of the content extracted from project files is performed before it is interpolated into the final configuration.
Audit Metadata