google-ads-account-audit
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external datasets, specifically Google Ads search term reports and campaign exports. These reports contain data generated by third parties (e.g., search queries from users on the internet), which serves as a potential vector for indirect prompt injection attacks where malicious instructions hidden in the data could attempt to bias the audit results.
- Ingestion points: The 'Collect data' process described in Step 1 of SKILL.md.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the provided data reports.
- Capability inventory: The skill primarily performs analytical tasks and checklist verification; it does not contain direct file-write or network-send capabilities in its provided instructions, though it recommends the use of external scripts for automation.
- Sanitization: There are no instructions for sanitizing or filtering the imported reports for potentially malicious strings.
Audit Metadata