omnibus-instrument-feature-flags
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by instructing the agent to store sensitive API keys in environment variables via the env-file-tools MCP server instead of hardcoding them (SKILL.md Step 6).
- [SAFE]: All identified dependencies (e.g., posthog-js, posthog-node, posthog-python) and network endpoints (e.g., us.i.posthog.com) are official PostHog vendor resources, presenting no third-party supply chain risk.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: The agent analyzes the user's codebase and dependency files in SKILL.md Step 1. Capability inventory: The agent can modify project files (Step 5) and update environment variables (Step 6). Sanitization: No explicit validation or filtering of the ingested codebase content is specified before the agent uses that data to perform actions.
Audit Metadata