instrument-feature-flags

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes project codebase files such as package.json and .env to detect the platform and existing configuration. This represents a standard ingestion surface for project metadata.
  • Ingestion points: Dependency files and environment configuration files in the project root (SKILL.md).
  • Boundary markers: No explicit markers are used to separate project data from instructions.
  • Capability inventory: The agent has capabilities to read/write files and execute the PostHog MCP 'projects-get' tool.
  • Sanitization: The skill instructions do not specify sanitization of the content read from project files before using it to plan the instrumentation.
  • [SAFE]: The skill follows security best practices for secret management by recommending environment variables and uses official vendor documentation and tools. No malicious patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 01:23 AM
Security Audit — agent-trust-hub — instrument-feature-flags