Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a scorecard tool, but its setup contract executes any `cli-printing-press` binary found in the current git repo without verification and then shadows the PATH for later calls, which is a risky behavior toward the user without evidence of malicious intent.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill does not fetch or execute the install itself, but its prerequisites and error paths instruct installing the required `cli-printing-press` binary via `go install ...@latest` from an individual-owned repository (`mvanhorn`), which is unofficial and mutable, so under the recall-first override it is rated medium.
mvanhorn/cli-printing-press
c9957c1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.