realtime-transport-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external, potentially untrusted source code repositories. This creates an attack surface where an adversary could place malicious instructions within the codebase (e.g., in comments or string literals) to influence the agent's behavior during the review process.\n
  • Ingestion points: The skill scans directories such as src/, app/, and packages/ for transport-related code (as defined in SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions are provided to separate the audited code from the agent's instructions, increasing the risk of the agent following embedded commands.\n
  • Capability inventory: The skill utilizes shell-based search tools (ripgrep) and involves high-level interpretation of source code logic, providing a significant interaction surface.\n
  • Sanitization: No specific sanitization or filtering of the content read from the codebase is described before processing.\n- [COMMAND_EXECUTION]: The skill includes shell command examples using ripgrep (rg) to locate code patterns within the local environment. While these are legitimate auditing tools and the commands themselves are static, their inclusion requires the agent to have shell execution capabilities to fulfill the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:59 PM
Security Audit — agent-trust-hub — realtime-transport-contracts