meta-ads-analyzer
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests and processes data from untrusted external Excel (.xlsx) reports (SKILL.md Step 2, Reference B.1). Maliciously crafted content within report fields (such as campaign names or ad copy) could attempt to influence the agent's behavior when the data is formatted into reports (HTML, DOCX, PPTX, MD) or passed to chained skills like 'ai-slop-reviewer'. However, the skill implements comprehensive data integrity checks and consistency validation (Reference H.1), and uses structured analysis modules which significantly mitigate the risk of accidental instruction execution.
Audit Metadata