marketing-kpi-dashboard-planner
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate marketing plans, which could be exploited to influence agent behavior.
- Ingestion points: The skill accepts user-supplied data for 'channels', 'funnel stage', 'stakeholders', and 'reporting goal' as defined in
SKILL.md. - Boundary markers: The instructions lack explicit delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings for the interpolated user data.
- Capability inventory: The skill has access to
ReadandWritetools as specified in the YAML frontmatter, which could be misused if the agent obeys instructions hidden within user inputs. - Sanitization: No sanitization, validation, or escaping logic is described for the input data before it is processed or used in tool calls.
Audit Metadata