Epistemic Guide
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent and privacy-conscious, but users should know it may steer sensitive conversations into Socratic questioning and may send claims to external fact-checking tools if they consent.
This skill appears safe to install as an instruction-only conversation aid, but expect it to challenge questionable claims on sensitive topics. For privacy, only approve external verification when you are comfortable sending the claim or query to the named search, fact-checking, or API service.
Findings (2)
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.
The agent may respond to some sensitive claims by questioning the user's reasoning rather than simply answering or continuing normally.
The skill can redirect sensitive-topic discussions into belief examination and Socratic questioning. This matches the stated purpose and is disclosed, but it is still a noticeable behavioral change users should expect.
Activate this skill when the user: ... States beliefs on sensitive topics: philosophy, religion, science, politics, conspiracy theories
Install this only if you want the agent to actively challenge potentially questionable claims; ask the agent to stop or switch modes if the questioning style is not desired.
If the user approves external checking, sensitive beliefs or claims may be sent to search engines, fact-checking services, or other configured systems.
The skill discloses that claim verification can transmit user claims or queries to external services or other configured tools. The visible workflow requires user consent, making this purpose-aligned, but the data flow is privacy-relevant.
When external verification is used, this skill may invoke: Web search tools (sends queries to search engines) - verify-claims skill (sends claims to fact-checking services) - Other configured skills or APIs
Decline external verification when discussing private or sensitive matters, or confirm which tool or service will be used before approving a check.