director-product-management
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is granted access to the
Bashtool. While no malicious commands are hardcoded in the prompt, this tool provides a high-privilege environment that could be exploited if the agent receives malicious instructions from external data. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. It ingests untrusted data through
WebSearchandReadtools and has significant capabilities to impact the system. - Ingestion points:
WebSearch,Read,Glob,Grep(defined inSKILL.mdtools and primary skills). - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore embedded instructions in external data.
- Capability inventory:
Bash,Write,Edit,Task(defined inSKILL.mdtools). - Sanitization: Absent. No specific sanitization or validation logic is defined for processing external inputs.
Audit Metadata