parse-ad-requirements
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted advertiser input. ● Ingestion point: Natural language input provided by advertisers in SKILL.md. ● Boundary markers: Absent; there are no instructions to delimit input or ignore embedded commands. ● Capability inventory: Data extraction for campaign management; no shell, file, or network code is present. ● Sanitization: Absent; the skill relies on prompt-level advice ('Be Conservative') rather than structural validation.
- [NO_CODE] (INFO): The skill contains only markdown instructions and no executable scripts, binaries, or dependency manifests.
Audit Metadata