meta-ads-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the command adkit status to verify if the vendor's command-line interface is installed in the user's environment. This check determines whether to provide automated campaign management or manual UI instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill searches for and reads the contents of ad-process.md and ad-brief.md from the user's project directory to customize its recommendations. This creates a surface for indirect prompt injection.
  • Ingestion points: Reads project-level files ad-process.md and ad-brief.md during the context-check phase.
  • Boundary markers: None identified; the skill is instructed to read the file and apply the preferences found within.
  • Capability inventory: The skill can execute shell commands via the AdKit CLI tool if present.
  • Sanitization: No explicit sanitization or filtering of the ingested file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 11:49 AM