meta-ads-campaign-builder

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it instructs the agent to process untrusted data from external sources.\n
  • Ingestion points: The skill gathers external data from product URLs, landing pages, and competitor names during the 'Intake' (Phase 0) and 'Audience Strategy' (Phase 2A) stages.\n
  • Boundary markers: There are no instructions or delimiters provided to tell the agent to ignore potential commands embedded within the external content it researches.\n
  • Capability inventory: The agent uses the web_search tool and has the ability to write files to the local file system (saving plans to the clients/ directory).\n
  • Sanitization: The skill does not define any validation or sanitization steps for the data retrieved from external URLs before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM