actionbook
What this skill does
Browser automation and web interaction tool for tasks like form filling, clicking buttons, and scraping websites.
github/actionbook - Data Exfiltration - 1.6k stars
Threat analysis
Skill info
pkg:github/actionbook/actionbook@26bf8a6?skill=actionbookAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
references/authentication.md
The use of $APP_USERNAME and $APP_PASSWORD environment variables in the CLI commands suggests that the tool may be handling sensitive credentials. If these variables are not properly secured, they couExcessive Agency
Excessive Agency via local-llm-review
SKILL.md
The skill description mentions that it can operate any website instantly, one tab or dozens, concurrently. This level of automation and control could be considered excessive agency if not properly conBadge
Add the Anomity scan badge for actionbook 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 actionbook? Report an issue or request a rescan.
