marketing-skills-collection

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its capability to ingest and process data from untrusted external sources during marketing research tasks.\n
  • Ingestion points: External content retrieved via the WebFetch tool and user-provided variables within the Product Context and marketing_brief templates in SKILL.md.\n
  • Boundary markers: The skill uses structured Markdown headers and YAML blocks to organize input, but it lacks specific instructions directing the agent to ignore potentially malicious commands embedded in fetched web content.\n
  • Capability inventory: The skill is granted access to the WebFetch tool for network access, Write for asset generation, and Task for sub-skill execution.\n
  • Sanitization: There are no explicit sanitization, filtering, or validation steps defined for data retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:09 AM