ads-generate
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user data and passes it to sub-agents.
- Ingestion points: The skill reads the contents of
campaign-brief.mdandbrand-profile.json(SKILL.md, Steps 2 & 6). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested files.
- Capability inventory: The skill spawns the
visual-designerandformat-adapteragents via the Task tool withcontext: fork, providing a channel for injected instructions to influence downstream agent behavior. - Sanitization: The skill does not describe any validation or escaping of the content read from these files before passing them to the sub-agents.
Audit Metadata