paid-ads-chatgpt

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code, scripts, or external dependencies. It consists entirely of markdown instructions intended to guide the AI agent's behavior during a specific task.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as campaign objectives and verified ads exports, which constitutes a potential surface for indirect prompt injection. However, since the skill does not define any capabilities for command execution, file system access, or network operations, the risk is negligible.
  • Ingestion points: Untrusted data enters the agent context via the primary input argument defined in the frontmatter.
  • Boundary markers: The instructions do not specify delimiters or warnings to ignore embedded instructions within the ingested data.
  • Capability inventory: No tools, scripts, or system commands are requested or defined.
  • Sanitization: No input sanitization or validation logic is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:14 PM
Security Audit — agent-trust-hub — paid-ads-chatgpt