ad-campaign-consolidation
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of high-level strategic instructions and evaluation criteria for marketing analysis. It does not include any executable scripts, shell commands, or network-enabled tools. The frontmatter does not request any dangerous capabilities, and the instructions explicitly state that the agent should only recommend and never execute changes.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as advertising account exports and user-provided configuration details.
- Ingestion points: The 'Workflow' section in
SKILL.mdinstructs the agent to inventory current account structures and read data exports directly if available. - Boundary markers: No specific delimiters or 'ignore instructions' warnings for the ingested data are defined.
- Capability inventory: The skill contains no automated tools, subprocess calls, or network operations. It is strictly limited to generating natural language plans and tables for a human user to review.
- Sanitization: No specific sanitization or filtering of external data is mentioned, as the data is used for quantitative analysis (conversions, spend, ROAS). The risk is minimal because the output is human-readable advice rather than code or automated commands.
Audit Metadata