manage-feature-flags

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is developed by the official vendor and uses standard project management patterns. It includes safety practices such as requiring human confirmation before destructive operations like archiving or disabling flags.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could contain malicious instructions.\n
  • Ingestion points: Flag display names and descriptions are read from the Mixpanel API (SKILL.md). The local codebase is searched for occurrences of flag keys (references/hygiene-and-cleanup.md).\n
  • Boundary markers: The instructions do not define specific delimiters to separate untrusted data from the system prompt.\n
  • Capability inventory: The agent has the ability to create, update, and archive flags via the Mixpanel MCP server.\n
  • Sanitization: No explicit sanitization or filtering logic is prescribed for data retrieved from the API or codebase search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 01:46 PM