advertising-compliance
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data such as marketing materials and websites.
- Ingestion points: Reviewing and drafting marketing materials, pitchbooks, and website content as specified in SKILL.md.
- Boundary markers: Absent; there are no instructions to use delimiters or to ignore commands within the analyzed data.
- Capability inventory: The skill frontmatter allows the use of Bash, Read, Write, and Edit tools.
- Sanitization: No sanitization or input validation mechanisms are defined.
Audit Metadata