ClawHub

Gaslighting Detector Skill

v1.0.2

Gaslighting Detector is an AI pattern checker for messages and conversations that leave you doubting your memory, judgment, or emotional reality. It spots ga...

⭐ 0· 113·0 current·0 all-time
bywes@imwyvern
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and SKILL.md all describe an analyst-style conversation helper. The skill requests no credentials, binaries, or config paths — which is proportionate for a conversational analysis tool.
ℹ
Instruction Scope
SKILL.md confines the agent to analyzing user-provided messages, giving a clear output format and safety guidance. It does include an explicit marketing/upgrade nudge pointing users to replyher.com after multiple exchanges, which steers users to an external site; this is a transparency/usability note rather than a technical risk. The instructions do not ask the agent to read local files, environment variables, or other unrelated system state.
✓
Install Mechanism
No install spec — instruction-only — so nothing is written to disk at install/runtime. A publish.sh developer script is present but is a local publishing helper (git push + npx clawhub publish) not executed at agent runtime.
✓
Credentials
No environment variables, secrets, or external credentials are requested. The README and SKILL.md mention a third-party brand (ReplyHer) and an external URL for upgrades, but no automatic data transmission to external endpoints is defined in the skill instructions.
✓
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges. The skill does not instruct modifying other skills or system configurations.
Assessment
This skill appears coherent with its stated purpose and doesn't request secrets or install code. Things to consider before installing: 1) The skill contains an explicit upsell directing users to replyher.com for ongoing tracking — verify the third-party site's privacy policy before sending sensitive details. 2) Do not paste identifying or highly sensitive information about yourself or others into any skill you don't control. 3) The included publish.sh is a developer convenience script (git + npx publish) and is not run by the agent, but it indicates the skill's author publishes to external services; check the skill source/owner trustworthiness if you plan to rely on it for ongoing support.

Like a lobster shell, security has layers — review code before you run it.

latestvk97d416m65d7xanegsb70r2dh584624k

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🔍🛡️ Clawdis

Comments