pi-goal
What this skill does
Persistent goal tracking for an AI agent, allowing users to set, update, and inspect long-running goals with status transitions and continuation prompts.
github/code-yeongyu - Obfuscation/Hidden Behavior - 67.6k stars
Threat analysis
Skill info
pkg:github/code-yeongyu/oh-my-openagent@ee81ab7?skill=pi-goalAssessments (2)
Obfuscation/Hidden Behavior
Obfuscation/Hidden Behavior via local-llm-review
src/goal/continuation.ts
The function `shouldQueueGoalContinuationAfterAgentEnd` and related logic may be used to silently re-engage the agent toward an active goal via hidden continuation prompts (`pi-goal-continuation` custSupply Chain
Supply Chain via local-llm-review
package.json
The `peerDependencies` include `@mariozechner/pi-ai`, `@mariozechner/pi-coding-agent`, and `@mariozechner/pi-tui` with version `*`, which could introduce risks if these dependencies are not strictly vBadge
Add the Anomity scan badge for pi-goal 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 pi-goal? Report an issue or request a rescan.
