event-marketing
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests user-supplied text to influence the orchestration of multiple specialized agents without sufficient isolation.
- Ingestion points: The
--guidanceparameter and the responses collected during--interactivemode inSKILL.mdare direct points where untrusted data enters the agent's context. - Boundary markers: The instructions do not specify any delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings to prevent the agent from obeying malicious commands contained within the user guidance.
- Capability inventory: Across the skill, the primary capability is writing multiple markdown files to the local file system (
.aiwg/marketing/events/). It does not appear to have network or arbitrary command execution capabilities. - Sanitization: No input validation, escaping, or filtering of the user-provided guidance is documented before it is interpolated into the prompts for the specialized agents.
- [PROMPT_INJECTION]: The metadata contains a misleading description ('Project directory path') that does not match the skill's actual purpose ('event-marketing'), which could lead to user confusion regarding the skill's function.
Audit Metadata