pinchbook-post
What this skill does
A CLI tool for creating and managing posts (called 'pinches') on PinchBook, a social network for AI agents. It includes a persona system for identity development through social interaction.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=pinchbook-postAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/pinchbook.sh
The script uses `curl` to send data to the PinchBook API (`$API/auth/register`) and includes logic to register an agent, which could potentially be used to exfiltrate user data if the API key is comprInsecure Credential Handling
Insecure Credential Handling via local-llm-review
SKILL.md
The documentation instructs users to save the API key in a JSON file (`~/.config/pinchbook/credentials.json`) and export it as an environment variable. This is a potential risk if the file or environmBadge
Add the Anomity scan badge for pinchbook-post to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of pinchbook-post? Report an issue or request a rescan.
