ad-campaign-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted campaign data from third-party platforms without explicit isolation or sanitization steps.
  • Ingestion points: Raw performance data provided by the user via CSV, pasted text, or screenshots (SKILL.md).
  • Boundary markers: Absent; there are no instructions to the agent to treat ad titles, keyword names, or other campaign data as untrusted content or to ignore embedded instructions.
  • Capability inventory: The skill instructs the agent to write formatted diagnostic reports to the local filesystem (SKILL.md).
  • Sanitization: Absent; no data validation, escaping, or filtering mechanisms are defined before the ingested content is analyzed and reported.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 01:07 PM