track-funding-rounds
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and installs the vendor's official CLI tool (@cargo-ai/cli) from the standard npm registry.
- [COMMAND_EXECUTION]: Uses shell commands to check for existing plugins in the environment, manage workspace session state, and execute data enrichment batches.
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: Company domains in the batch execution section of SKILL.md. 2. Boundary markers: Absent in the interpolation template. 3. Capability inventory: Data enrichment via the cargo-ai CLI and session upsert commands. 4. Sanitization: None explicitly defined in the prompt instructions. This reflects the standard data processing surface for enrichment tools.
- [SAFE]: The skill implements cost-discipline practices by instructing the agent to sample records and get user approval for full runs. It also explicitly requires user consent before attempting to star the repository on GitHub, preventing unauthorized social actions.
Audit Metadata