flightphp

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It is designed to ingest and process untrusted data from the user's local codebase (during migration tasks) and from an external documentation service (Context7).
  • Ingestion points: Local files (controllers, models, etc.) read from the user's project; external documentation content fetched via the mcp__plugin_context7_context7 tool.
  • Boundary markers: The instructions lack delimiters or warnings to treat processed content as data rather than instructions, which could allow malicious content within those files to influence the agent's output or actions.
  • Capability inventory: The agent typically retains file system and shell execution capabilities while using this skill.
  • Sanitization: There are no instructions for validating, escaping, or filtering the ingested content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 09:28 PM
Security Audit — agent-trust-hub — flightphp