setup-ralph
What this skill does
Setup and configure Ralph Wiggum autonomous coding loops
github/glittercowboy - Excessive Agency - 2k stars
Threat analysis
Skill info
pkg:github/glittercowboy/taches-cc-resources@1757615?skill=setup-ralphAssessments (2)
Excessive Agency
Excessive Agency via local-llm-review
README.md
The skill allows Ralph to run in non-Docker mode with --dangerously-skip-permissions, giving it full access to the system as the user. This could lead to unintended modifications if not carefully moniPrivilege Escalation
Privilege Escalation via local-llm-review
templates/loop-docker.sh
The script uses --dangerously-skip-permissions flag which allows execution of commands without confirmation. This could be used to perform actions that require elevated privileges if not properly restBadge
Add the Anomity scan badge for setup-ralph 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 setup-ralph? Report an issue or request a rescan.
