outreach-campaign

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The workflow involves executing bash commands using the composio CLI tool to search for available tools and execute campaign creation logic.
  • [PROMPT_INJECTION]: The skill processes untrusted user input via the $ARGUMENTS variable to define campaign details, creating a data ingestion surface.
  • Ingestion points: User input enters the context through $ARGUMENTS in SKILL.md.
  • Boundary markers (absent): There are no delimiters or "ignore embedded instructions" warnings present for the input data.
  • Capability inventory: The skill utilizes shell command execution via the Bash tool in SKILL.md.
  • Sanitization (absent): No escaping, validation, or filtering of the user input is described before it is used to construct shell command payloads.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external outreach services such as Lemlist, Reply.io, and Woodpecker via the Composio interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — outreach-campaign