gtm-diff
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Google Tag Manager API and a local log file, presenting a surface for indirect instructions to be processed by the agent.
- Ingestion points: The skill reads data from
gtm-implementation-log.jsonand fetches tag, trigger, and variable definitions from the GTM API. - Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore instructions that might be embedded within the GTM container data (e.g., inside a Tag name or HTML body).
- Capability inventory: The skill is limited to reading local configuration files (
gtm-config.json,gtm-token.json) and performing API list/read operations. It does not possess file-write or shell execution capabilities. - Sanitization: There is no evidence of sanitization or filtering applied to the external data before it is displayed in the diff report.
Audit Metadata