lead-enrich

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run Bash commands using the composio CLI. User input from $ARGUMENTS is embedded into these shell commands (e.g., inside the data payload for composio execute), which can lead to command injection if the input contains shell metacharacters like semicolons or backticks.
  • [PROMPT_INJECTION]: This skill exhibits an indirect prompt injection surface by processing untrusted user data without validation or delimiters.
  • Ingestion points: User input enters via the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: Absent. The input is placed directly into command-line arguments.
  • Capability inventory: The skill uses the Bash tool to perform searches and tool executions.
  • Sanitization: No sanitization or escaping logic is present to handle malicious input before it reaches the command line.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:13 PM
Security Audit — agent-trust-hub — lead-enrich