google-ads-strategy
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command
adkit statusto verify the installation of the vendor's CLI tool. While this is a vendor-owned resource related to the skill's functionality, it represents an automated command execution pattern. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from the local environment and applies it to its logic without sanitization.
- Ingestion points: The agent is instructed to search for and read the content of
ad-process.mdandad-brief.mdfrom the project directory inSKILL.md. - Boundary markers: None. The skill lacks instructions to delimit the content or ignore potentially malicious instructions embedded in these configuration files.
- Capability inventory: The skill has the ability to execute shell commands (e.g.,
adkit status). - Sanitization: No validation or sanitization is performed on the data read from the local files before it is processed.
Audit Metadata