instrument-feature-flags
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official PostHog SDKs from trusted registries like NPM, PyPI, Maven, and RubyGems. It also includes the standard PostHog web snippet which loads the core library from PostHog's infrastructure (e.g., assets.i.posthog.com).
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the user's codebase to detect frameworks and configurations. This represents an attack surface where malicious code or comments in the analyzed files could attempt to influence the agent's behavior. Ingestion points: SKILL.md Step 1 (codebase analysis); Boundary markers: Absent; Capability inventory: File read/write operations and network requests via SDKs; Sanitization: Absent.
- [SAFE]: The skill follows security best practices by explicitly instructing the agent to use environment variables or authorized MCP tools for managing project tokens instead of hardcoding them.
Audit Metadata