content-creation-and-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external source material to generate drafts and update brand/strategy files, creating a risk that malicious instructions within those source assets could influence the agent's behavior.
- Ingestion points: The skill accepts source material including ideas, notes, transcripts, and outlines (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings to the model to ignore potential instructions embedded within the provided source materials.
- Capability inventory: The skill has the capability to write files to the local file system (drafts) and modify existing strategy/context files such as
strategy/brand.md,about/me.md, andcontent/ideas.md(SKILL.md). - Sanitization: No sanitization or validation steps are defined for the source material before it is used to generate or update content.
Audit Metadata