is-bullshit
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill is coherently focused on optional hallucination checking and shows no evidence of hidden code, credentials, exfiltration, or destructive behavior.
This skill appears safe to install as an optional fact-checking aid. Leave it disabled unless you want automatic fact-check sections after responses, and be aware that those sections may summarize earlier parts of the conversation.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
If turned on, replies may always include an extra fact-check section, which could be distracting or reveal summaries of prior exchanges in the same chat.
The skill can alter the assistant's normal output behavior by automatically appending fact checks, but this behavior is disclosed and tied to an explicit enable setting.
When config `enable = true`, this skill **MUST automatically show** fact check after **EVERY response**, WITHOUT waiting for user to ask
Only enable always-on checking if you want every assistant response to include this extra review; otherwise leave the default disabled setting.
The fact-check output may restate previous conversation details, so users should be mindful when the chat contains sensitive information.
The skill intentionally reviews prior conversation context and may summarize earlier user questions and assistant answers as part of its fact-check output.
Look at what tools were called throughout the **entire conversation history**
Avoid enabling automatic fact checks in chats where repeating or summarizing previous sensitive content would be undesirable.