workflow-marketing-strategy
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities.
- Ingestion points: External data is ingested into the agent context via the
/web-researchand/deep-researchsteps defined inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit warnings to the agent to disregard potential instructions embedded within the retrieved research content.
- Capability inventory: The skill utilizes
TaskCreateand various research/strategy tools; no high-risk capabilities such as arbitrary code execution or file-system writing were identified in the skill body. - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata