performance-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes performance data from external campaign management tools, which represents a potential indirect prompt injection surface if campaign names or metadata were manipulated.
- Ingestion points: Performance figures and outliers are read via
metrics.account-overview,metrics.sequence, andsender.healthtools as described inSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' warnings for the data being analyzed.
- Capability inventory: The skill's primary capabilities are analytical; it includes one confirmed action (pausing campaigns) via the
campaign-launchskill, but lacks network or file-system write access. - Sanitization: No specific sanitization or escaping of the metrics data is mentioned in the prompt logic.
- [SAFE]: The skill enforces a human-in-the-loop requirement, stating it is 'Read-only by default' and that actions like pausing campaigns only occur on 'explicit approval'.
- [SAFE]: Tool usage is limited to scoped diagnostic and measurement operations, adhering to the principle of least privilege for its stated purpose.
Audit Metadata