agent-actions
What this skill does
The skill provides guidance on designing and reviewing Agentforce actions, including best practices for action contracts, error handling, confirmation requirements, and security considerations. It is
github/pranavnagrecha - Code Analysis - 8 stars
Threat analysis
Skill info
pkg:github/PranavNagrecha/AwesomeSalesforceSkills@14f9b24?skill=agent-actionsAssessments (1)
Code Analysis
Code Analysis via local-llm-review
scripts/check_agent_actions.py
The script contains regex patterns that may be used to detect potentially unsafe or poorly designed Apex invocable actions (e.g., checking for 'create', 'update', 'delete', etc.). While this is a legiBadge
Add the Anomity scan badge for agent-actions 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 agent-actions? Report an issue or request a rescan.
