content-groups
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data provided by the Google Search Console API, including site URLs, path structures, and user-defined group rules.
- Ingestion points: Data enters the agent context through tools like 'list_content_groups' and 'breakdown_by_path', which return site-specific URL patterns and metadata.
- Boundary markers: The skill does not specify explicit delimiters to separate external data from system instructions.
- Capability inventory: The skill possesses write capabilities, including 'create_content_group', 'update_content_group', and 'delete_content_group'.
- Sanitization: The skill effectively mitigates risk by requiring mandatory user confirmation before any write operations are executed and by restricting regular expressions to the RE2 syntax to prevent catastrophic backtracking.
- [SAFE]: Extensive review of the skill's instructions and logic revealed no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution. The skill's operations are consistent with its primary purpose of SEO data analysis and management.
Audit Metadata