skills/naimsolong/ai-software-agency/specialist-project-management-project-management-studio-producer/Gen Agent Trust Hub
specialist-project-management-project-management-studio-producer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input by interpolating it into a sub-agent prompt.
- Ingestion points: User input is accepted via the
{the_user_question}placeholder within theAgenttool call inSKILL.md. - Boundary markers: The skill does not use delimiters (like XML tags or triple quotes) or specific instructions to isolate user input from the agent's system instructions.
- Capability inventory: The skill uses the
Agenttool to spawn a persona focused on strategic planning and reporting; it does not explicitly invoke high-risk capabilities like file system writes or arbitrary command execution. - Sanitization: There is no evidence of input validation, escaping, or filtering applied to the user-provided data before it is processed.
Audit Metadata