apollo-lead-gen

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the instructions and workflow revealed no malicious patterns, obfuscation, or unauthorized access attempts. The skill operates within the expected parameters for lead generation tasks.
  • [COMMAND_EXECUTION]: The skill uses the composio CLI tool for linking accounts, searching for capabilities, and executing API calls. These actions are consistent with the vendor's intended use of the toolset.
  • [DATA_EXPOSURE]: Lead data is exported to a local CSV file (./leads-<campaign>.csv). No sensitive system configuration files or environment variables are accessed or transmitted.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied parameters for search filters such as job titles and company industries.
  • Ingestion points: User input for ICP (Ideal Customer Profile) filters specified in the workflow and prompt sections of SKILL.md.
  • Boundary markers: Absent; user strings are directly used in JSON search payloads.
  • Capability inventory: Bash (via composio), Write (for CSV generation).
  • Sanitization: Absent; the skill relies on the structured nature of the JSON payload for the search command.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:24 PM
Security Audit — agent-trust-hub — apollo-lead-gen