money-ads
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses local configuration files at
~/.smtm/projects/{slug}/profile.jsonto determine business types and platform fit. Access to hidden directories in the user's home folder allows the agent to read metadata that may contain sensitive business logic or project history. - [INDIRECT_PROMPT_INJECTION]: The skill uses external configuration data from project profiles to drive high-impact decision-making and tool usage, creating a potential injection surface.
- Ingestion points: Data is read from
~/.smtm/projects/{slug}/profile.jsonat runtime to determine campaign strategy. - Boundary markers: There are no instructions provided to the agent to treat this configuration data as untrusted or to ignore any command-like instructions embedded within the JSON fields.
- Capability inventory: The skill has significant capabilities, including the automated provisioning of Google Ads MCC sub-accounts, conversion pixel setup, and daily budget management.
- Sanitization: The skill lacks defined validation or sanitization protocols for the ingested profile data before it is interpolated into decision-making logic for campaign scaling and platform selection.
Audit Metadata