apollo-to-cargo

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the npm registry and provides instructions to download additional vendor skills using npx.- [COMMAND_EXECUTION]: The skill executes multiple command-line operations, including npm for package management, cargo-ai for authentication and data enrichment actions, and gh for GitHub repository interaction.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided CSV files (e.g., apollo-q3-export.csv) to perform batch enrichment tasks, which could potentially contain malicious content if the source data is untrusted.
  • Ingestion points: User-provided CSV files referenced in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from interpreting data within the CSV as instructions.
  • Capability inventory: The agent uses cargo-ai to perform network-based enrichment and batch actions.
  • Sanitization: There is no explicit sanitization or validation of the CSV content described in the skill instructions.- [PERSISTENCE]: The skill creates a configuration file at ~/.config/cargo-ai/.star-asked to track user interaction state across sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 08:46 PM