Prompt Crafter
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (ignore-previous-instructions); human review is required before treating this skill as clean.
This skill appears safe to install as a prompt-writing reference. Be aware that it includes adversarial prompt examples for testing; treat those examples as defensive test inputs, not as instructions to bypass existing rules. ClawScan detected prompt-injection indicators (ignore-previous-instructions), so this skill requires review even though the model response was benign.
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Users may see prompt-injection language in the guide, but the artifact uses it to teach defensive testing rather than to override user or system intent.
This contains prompt-injection wording, but it is presented as an example of adversarial input testing under 'Production Safety,' not as an instruction for the agent to follow.
4. **Test adversarial inputs.** "Ignore all previous instructions..." is real.
Use the phrase only as a test case for prompt robustness, and keep untrusted user content clearly separated from trusted instructions.