pre-define
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted user requests to drive local filesystem exploration.
- Ingestion points: User input provided as arguments to the
/pre-defineor$pre-definecommands (SKILL.md). - Boundary markers: Absent. The skill does not use delimiters or explicit instructions to ignore potentially malicious commands embedded in the user's request.
- Capability inventory: The skill is instructed to perform keyword searches, semantic searches via the
serenatool, directory structure audits, and data schema analysis (SKILL.md). - Sanitization: Absent. There are no guidelines provided to filter or validate user input before it is used to perform read-based search operations across the local environment.
Audit Metadata