domain-embedded

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a dynamic context injection pattern in SKILL.md to execute cat .cargo/config.toml. This command runs automatically at skill load time to provide the agent with environmental context regarding the project's target configuration. This is a legitimate development workflow but involves shell command execution.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the ingestion of untrusted local data.
  • Ingestion points: Content is read from .cargo/config.toml in SKILL.md using shell execution.
  • Boundary markers: The injected configuration data lacks delimiters or explicit warnings to the agent to ignore any instructions embedded within the file.
  • Capability inventory: As a development-focused skill, it is used in environments where the agent typically possesses file system access and shell execution capabilities.
  • Sanitization: No filtering or sanitization is applied to the content of the configuration file before it is presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 05:48 PM
Security Audit — agent-trust-hub — domain-embedded