metronome-csm-reviews
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill exclusively utilizes official Metronome API endpoints (api.metronome.com and staging.api.metronome.com) for all operations, which is appropriate for a skill authored by metronome-industries.
- [SAFE]: Sensitive authentication is managed via the $METRONOME_API_TOKEN environment variable, adhering to secure secret management practices.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes data from external API responses (e.g., customer names, contract details, invoice data).
- Ingestion points: Data is retrieved via shared API endpoints defined in SKILL.md and processed in all reference files (references/anomaly-detection.md, references/commit-health.md, references/portfolio-briefing.md, references/renewal-prep.md).
- Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential instructions embedded in the API data.
- Capability inventory: The skill's capabilities are limited to read-only API data retrieval and numerical analysis. It lacks capabilities for shell command execution, file system modification, or non-vendor network operations.
- Sanitization: No explicit sanitization of API-provided strings is performed; however, the risk is mitigated by the read-only nature of the tool and the focus on structured financial data.
Audit Metadata