campaign-kickoff
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text via the
--guidanceparameter and--interactivemode to tailor the campaign approach. This represents an attack surface where instructions provided as 'guidance' could potentially influence the behavior of the orchestrated agents. - Ingestion points: The
--guidanceparameter and user responses during interactive discovery. - Boundary markers: No explicit boundary markers or 'ignore embedded instructions' directives are specified for the interpolated guidance.
- Capability inventory: The skill performs file system writes to create the campaign structure in
.aiwg/marketing/campaigns/and orchestrates several sub-agents (Strategist, Researcher, etc.). - Sanitization: No evidence of input sanitization or keyword filtering for the user-provided guidance string is documented.
Audit Metadata