messages-ops

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing untrusted external data.
  • Ingestion points: The skill explicitly reads and processes content from 'local messages', 'X / social DM', and 'browser-gated message surfaces' as part of its retrieval workflow in SKILL.md.
  • Boundary markers: No explicit instructions are provided to use delimiters or ignore instructions embedded within the retrieved messages, increasing the risk that an attacker-controlled message could hijack the agent's behavior.
  • Capability inventory: The skill is designed to retrieve, inspect, and summarize message threads, and can potentially hand off data to other skills like knowledge-ops or lead-intelligence.
  • Sanitization: There are no instructions for sanitizing, escaping, or validating the content of the messages or one-time codes before they are output or passed to other tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — messages-ops